{"source":"AIMap","schema":"benchmarks/v1","updated":"2026-10-22","generatedAt":"2026-10-22T12:12:50.880Z","note":"Scores are copied from public leaderboards and datasets, never estimated. sourceType: official = benchmark maintainers' leaderboard; independent = third-party evaluator ran it (Epoch AI); vendor = self-reported/submitted by the developer; paper = paper or tech report; compiled = Epoch AI compilation without per-row origin. \"best\" = best score on the benchmark's main setting, preferring official/independent over vendor numbers. Respect each source's licence (see sources[].license / policy).","counts":{"results":3086,"models":1079,"benchmarks":23},"sources":[{"id":"lmarena","name":"LMArena leaderboard dataset","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","site":"https://lmarena.ai/leaderboard","license":"CC BY 4.0","policy":"open","type":"official","attribution":"LMArena, Arena Leaderboard Dataset (Hugging Face), CC BY 4.0","access":"Hugging Face datasets-server JSON API (split \"latest\")","lastFetched":"2026-10-10","fetchStatus":"error"},{"id":"epoch","name":"Epoch AI Benchmarking Hub","url":"https://epoch.ai/data/benchmark_data.zip","site":"https://epoch.ai/benchmarks","license":"CC BY 4.0","policy":"open","type":"independent","attribution":"Epoch AI, 'Capabilities & benchmarking', https://epoch.ai/benchmarks (CC BY 4.0)","access":"Official ZIP of CSV files","lastFetched":"2026-10-22","fetchStatus":"ok"},{"id":"swebench","name":"SWE-bench leaderboards (swebench.com)","url":"https://raw.githubusercontent.com/SWE-bench/swe-bench.github.io/master/data/leaderboards.json","site":"https://www.swebench.com/","license":"No explicit licence (NOASSERTION) – factual scores only, with citation","policy":"facts","type":"official","attribution":"SWE-bench team, swebench.com leaderboards","access":"leaderboards.json in the site's GitHub repo","lastFetched":"2026-10-22","fetchStatus":"ok"},{"id":"livecodebench","name":"LiveCodeBench leaderboard","url":"https://livecodebench.github.io/performances_generation.json","site":"https://livecodebench.github.io/leaderboard.html","license":"No explicit licence on the site repo (benchmark code MIT) – factual scores only, with citation","policy":"facts","type":"official","attribution":"LiveCodeBench (Jain et al.), livecodebench.github.io","access":"performances_generation.json (per-problem pass@1); we average it","lastFetched":"2026-10-22","fetchStatus":"ok"},{"id":"evalplus","name":"EvalPlus leaderboard","url":"https://evalplus.github.io/results.json","site":"https://evalplus.github.io/leaderboard.html","license":"Apache-2.0 (site repo)","policy":"open","type":"official","attribution":"EvalPlus team, evalplus.github.io","access":"results.json","lastFetched":"2026-10-22","fetchStatus":"ok"},{"id":"bfcl","name":"Berkeley Function Calling Leaderboard (BFCL)","url":"https://gorilla.cs.berkeley.edu/data_overall.csv","site":"https://gorilla.cs.berkeley.edu/leaderboard.html","license":"Apache-2.0 (gorilla repo)","policy":"open","type":"official","attribution":"Gorilla / BFCL team, UC Berkeley","access":"data_overall.csv","lastFetched":"2026-10-22","fetchStatus":"ok"},{"id":"tau2","name":"τ²-bench leaderboard submissions","url":"https://github.com/sierra-research/tau2-bench/tree/main/web/leaderboard/public/submissions","site":"https://taubench.com/","license":"MIT (repo)","policy":"open","type":"official","attribution":"Sierra Research, τ²-bench","access":"submission.json files in the GitHub repo","lastFetched":"2026-10-22","fetchStatus":"ok"},{"id":"mmlupro","name":"MMLU-Pro leaderboard (TIGER-Lab)","url":"https://huggingface.co/datasets/TIGER-Lab/mmlu_pro_leaderboard_submission","site":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","license":"Apache-2.0 (dataset)","policy":"open","type":"official","attribution":"TIGER-Lab, MMLU-Pro leaderboard","access":"results.csv in the HF dataset","lastFetched":"2026-10-22","fetchStatus":"ok"},{"id":"openllm","name":"Hugging Face Open LLM Leaderboard v2 (archived)","url":"https://huggingface.co/datasets/open-llm-leaderboard/contents","site":"https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard","license":"No licence tag – factual scores only, with citation","policy":"facts","type":"official","attribution":"Hugging Face, Open LLM Leaderboard (archived 2025)","access":"HF datasets-server JSON API; we keep only models published by the original developers","status":"archived","lastFetched":"2026-10-22","fetchStatus":"ok"},{"id":"arcprize","name":"ARC Prize leaderboard","url":"https://arcprize.org/leaderboard","site":"https://arcprize.org/leaderboard","license":"ARC Prize Terms: no copying/aggregation for commercial purposes without permission","policy":"limited","type":"official","attribution":"ARC Prize Foundation, arcprize.org/leaderboard","access":"Only the top entries per set are kept as short factual citations; see the official page for the full list","lastFetched":"2026-10-22","fetchStatus":"ok"},{"id":"cmmlu","name":"CMMLU leaderboard (GitHub README)","url":"https://github.com/haonan-li/CMMLU","site":"https://github.com/haonan-li/CMMLU","license":"CC BY-NC-SA 4.0","policy":"limited","type":"official","attribution":"Li et al., CMMLU (CC BY-NC-SA 4.0)","access":"Top entries of the README table only, with citation","lastFetched":"2026-10-22","fetchStatus":"ok"},{"id":"ceval","name":"C-Eval (GitHub README, initial release table)","url":"https://github.com/hkust-nlp/ceval","site":"https://cevalbenchmark.com/static/leaderboard.html","license":"Code MIT; dataset CC BY-NC-SA 4.0","policy":"limited","type":"official","attribution":"Huang et al., C-Eval","access":"README table (2023). The live leaderboard site was unreachable from our network on 2026-10-10.","lastFetched":"2026-10-22","fetchStatus":"ok"},{"id":"artificialanalysis","name":"Artificial Analysis","url":"https://artificialanalysis.ai/","site":"https://artificialanalysis.ai/leaderboards/models","license":"Free API requires an API key and attribution; no open bulk data","policy":"link-only","type":"independent","attribution":"Artificial Analysis","access":"Not collected – link only","lastFetched":null,"fetchStatus":"link-only"},{"id":"superclue","name":"SuperCLUE","url":"https://www.superclueai.com/","site":"https://www.superclueai.com/","license":"No open data interface","policy":"link-only","type":"independent","attribution":"CLUE / SuperCLUE","access":"Not collected – link only","lastFetched":null,"fetchStatus":"link-only"},{"id":"scale","name":"Scale AI SEAL leaderboards (SWE-bench Pro, HLE)","url":"https://scale.com/leaderboard","site":"https://scale.com/leaderboard","license":"No open data interface","policy":"link-only","type":"official","attribution":"Scale AI","access":"Not collected – link only","lastFetched":null,"fetchStatus":"link-only"}],"benchmarks":[{"id":"lmarena-text","name":"LMArena Text","category":"preference","unit":"Elo","higherIsBetter":true,"status":"active","primaryVariant":"overall-style-control","officialUrl":"https://lmarena.ai/leaderboard/text","description":{"en":"Crowd-sourced arena (formerly LMSYS Chatbot Arena): users chat with two anonymous models and vote for the better answer; votes are turned into a Bradley–Terry rating.","zh-hans":"众包对战榜（原 LMSYS Chatbot Arena）：用户同时与两个匿名模型对话并投票，投票结果换算成 Bradley–Terry 评分。"},"measures":{"en":"Human preference in open-ended chat (overall category, with style control).","zh-hans":"开放式对话中的人类偏好（总榜，开启“风格控制”）。"},"limitations":{"en":"Preference is not correctness; answer length and formatting sway votes; providers can test many private variants before release; scores are relative and drift as models are added.","zh-hans":"偏好不等于正确；回答长度和排版会影响投票；厂商可在发布前私下测试多个版本；分数是相对值，会随新模型加入而漂移。"},"contaminationRisk":"low","stats":{"results":414,"models":381,"latest":"2026-10-08","bySourceType":{"official":414}},"sources":["lmarena"],"pages":{"en":"https://aimap.page/en/benchmarks/lmarena-text/","zh-hans":"https://aimap.page/zh-hans/benchmarks/lmarena-text/"},"record":"https://aimap.page/api/benchmarks/lmarena-text.json"},{"id":"lmarena-webdev","name":"LMArena WebDev","category":"coding","unit":"Elo","higherIsBetter":true,"status":"active","primaryVariant":"overall","officialUrl":"https://lmarena.ai/leaderboard/webdev","description":{"en":"Arena where two models each build a web app from the same prompt and users vote on the result.","zh-hans":"两个模型按同一需求各写一个网页应用，由用户投票选出更好的那个。"},"measures":{"en":"Human preference for generated web apps (front-end coding).","zh-hans":"用户对生成网页应用（前端编码）的偏好。"},"limitations":{"en":"Visual polish can outweigh code quality; same preference biases as the text arena.","zh-hans":"视觉效果可能压过代码质量；存在与文本竞技场相同的偏好偏差。"},"contaminationRisk":"low","stats":{"results":141,"models":127,"latest":"2026-10-08","bySourceType":{"official":141}},"sources":["lmarena"],"pages":{"en":"https://aimap.page/en/benchmarks/lmarena-webdev/","zh-hans":"https://aimap.page/zh-hans/benchmarks/lmarena-webdev/"},"record":"https://aimap.page/api/benchmarks/lmarena-webdev.json"},{"id":"lmarena-vision","name":"LMArena Vision","category":"multimodal","unit":"Elo","higherIsBetter":true,"status":"active","primaryVariant":"overall-style-control","officialUrl":"https://lmarena.ai/leaderboard/vision","description":{"en":"Arena for image-understanding chats: users upload images, compare two anonymous models and vote.","zh-hans":"图像理解对战：用户上传图片，比较两个匿名模型的回答并投票。"},"measures":{"en":"Human preference on image + text questions.","zh-hans":"图文问答中的人类偏好。"},"limitations":{"en":"Fewer votes than the text arena, so wider confidence intervals.","zh-hans":"票数少于文本竞技场，置信区间更宽。"},"contaminationRisk":"low","stats":{"results":159,"models":143,"latest":"2026-10-02","bySourceType":{"official":159}},"sources":["lmarena"],"pages":{"en":"https://aimap.page/en/benchmarks/lmarena-vision/","zh-hans":"https://aimap.page/zh-hans/benchmarks/lmarena-vision/"},"record":"https://aimap.page/api/benchmarks/lmarena-vision.json"},{"id":"open-llm-leaderboard","name":"Open LLM Leaderboard v2","category":"general","unit":"%","higherIsBetter":true,"status":"archived","primaryVariant":"average","officialUrl":"https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard","description":{"en":"Hugging Face's leaderboard of open-weight models, scored on IFEval, BBH, MATH Lvl 5, GPQA, MuSR and MMLU-Pro with normalised scores. The leaderboard was archived in 2025 and no longer accepts submissions.","zh-hans":"Hugging Face 的开放权重模型排行榜，用 IFEval、BBH、MATH 第 5 级、GPQA、MuSR、MMLU-Pro 六项归一化打分。该榜已于 2025 年归档，不再接受新提交。"},"measures":{"en":"Average of six normalised academic benchmarks, run by Hugging Face with the same harness.","zh-hans":"由 Hugging Face 用同一套评测框架跑出的六项学术基准归一化平均分。"},"limitations":{"en":"Archived: no models after early 2025. Only open-weight models. We keep only models published by their original developers (no merges or community fine-tunes).","zh-hans":"已归档：不含 2025 年初以后的模型；只有开放权重模型。本站只保留原厂发布的模型，不收社区合并/微调版本。"},"contaminationRisk":"high","stats":{"results":311,"models":294,"latest":"2025-03-13","bySourceType":{"official":311}},"sources":["openllm"],"pages":{"en":"https://aimap.page/en/benchmarks/open-llm-leaderboard/","zh-hans":"https://aimap.page/zh-hans/benchmarks/open-llm-leaderboard/"},"record":"https://aimap.page/api/benchmarks/open-llm-leaderboard.json"},{"id":"artificial-analysis","name":"Artificial Analysis Intelligence Index","category":"general","unit":"index","higherIsBetter":true,"status":"link-only","primaryVariant":null,"officialUrl":"https://artificialanalysis.ai/leaderboards/models","description":{"en":"Independent composite index that runs a battery of evaluations plus price and speed measurements across API models.","zh-hans":"独立机构对各家 API 模型统一跑一组评测，并测价格与速度，合成综合指数。"},"measures":{"en":"Composite intelligence, price, latency and throughput.","zh-hans":"综合能力、价格、延迟和吞吐。"},"limitations":{"en":"Not collected here: the free API needs a key and attribution and there is no open bulk dataset. Use the link for current numbers.","zh-hans":"本站未采集：其免费 API 需要密钥和署名，没有开放的批量数据。最新数据请看官方页面。"},"contaminationRisk":"medium","stats":{"results":0,"models":0,"latest":null,"bySourceType":{}},"sources":["artificialanalysis"],"pages":{"en":"https://aimap.page/en/benchmarks/artificial-analysis/","zh-hans":"https://aimap.page/zh-hans/benchmarks/artificial-analysis/"},"record":null},{"id":"livecodebench","name":"LiveCodeBench","category":"coding","unit":"%","higherIsBetter":true,"status":"stale","primaryVariant":"codegen-2025","officialUrl":"https://livecodebench.github.io/leaderboard.html","description":{"en":"Coding problems collected continuously from LeetCode, AtCoder and Codeforces with their release dates, so models can be scored only on problems published after their training cut-off.","zh-hans":"持续从 LeetCode、AtCoder、Codeforces 收集带发布日期的编程题，可以只用模型训练截止日之后的新题来评分。"},"measures":{"en":"pass@1 on code generation. We average the official per-problem results for problems dated 2025-01-01 or later.","zh-hans":"代码生成 pass@1。本站对官方逐题结果中 2025-01-01 及以后的题目求平均。"},"limitations":{"en":"The public leaderboard file has not been updated since August 2025, so recent models are missing. Our window average can differ slightly from the site's default view.","zh-hans":"公开榜单文件自 2025 年 8 月起没有更新，缺少新模型；本站的时间窗平均值与官网默认视图可能略有差异。"},"contaminationRisk":"low","stats":{"results":22,"models":22,"latest":"2025-04-07","bySourceType":{"official":22}},"sources":["livecodebench"],"pages":{"en":"https://aimap.page/en/benchmarks/livecodebench/","zh-hans":"https://aimap.page/zh-hans/benchmarks/livecodebench/"},"record":"https://aimap.page/api/benchmarks/livecodebench.json"},{"id":"gpqa-diamond","name":"GPQA Diamond","category":"science","unit":"%","higherIsBetter":true,"status":"active","primaryVariant":"epoch","officialUrl":"https://github.com/idavidrein/gpqa","description":{"en":"198 graduate-level multiple-choice questions in biology, physics and chemistry written to be 'Google-proof'.","zh-hans":"198 道研究生水平的生物、物理、化学选择题，设计为“搜不到答案”。"},"measures":{"en":"Expert-level scientific reasoning. Scores here are Epoch AI's own runs (accuracy, best across scorers).","zh-hans":"专家级科学推理。本站分数来自 Epoch AI 自己的统一评测（准确率）。"},"limitations":{"en":"Only 198 questions, so ±3 points is noise; random guessing gives 25%; top models are close to saturation.","zh-hans":"只有 198 题，3 个百分点以内的差距基本是噪声；随机猜答案也有 25%；头部模型接近饱和。"},"contaminationRisk":"medium","stats":{"results":282,"models":217,"latest":"2026-10-19","bySourceType":{"independent":282}},"sources":["epoch"],"pages":{"en":"https://aimap.page/en/benchmarks/gpqa-diamond/","zh-hans":"https://aimap.page/zh-hans/benchmarks/gpqa-diamond/"},"record":"https://aimap.page/api/benchmarks/gpqa-diamond.json"},{"id":"mmlu","name":"MMLU","category":"knowledge","unit":"%","higherIsBetter":true,"status":"saturated","primaryVariant":null,"officialUrl":"https://github.com/hendrycks/test","description":{"en":"About 14,000 multiple-choice questions over 57 subjects, from elementary maths to law and medicine.","zh-hans":"约 1.4 万道选择题，覆盖 57 个学科，从初等数学到法律、医学。"},"measures":{"en":"Broad academic knowledge (usually 5-shot exact match). Data compiled by Epoch AI from papers, model reports and HELM.","zh-hans":"广泛的学科知识（通常 5-shot 精确匹配）。数据由 Epoch AI 从论文、模型报告和 HELM 汇编。"},"limitations":{"en":"Saturated at the top; studies found a share of mislabelled questions; prompt format changes scores by several points.","zh-hans":"头部已饱和；研究发现部分题目答案有误；提示格式不同可让分数差好几个点。"},"contaminationRisk":"high","stats":{"results":198,"models":158,"latest":"2024-12-26","bySourceType":{"paper":111,"vendor":7,"official":80}},"sources":["epoch"],"pages":{"en":"https://aimap.page/en/benchmarks/mmlu/","zh-hans":"https://aimap.page/zh-hans/benchmarks/mmlu/"},"record":"https://aimap.page/api/benchmarks/mmlu.json"},{"id":"mmlu-pro","name":"MMLU-Pro","category":"knowledge","unit":"%","higherIsBetter":true,"status":"active","primaryVariant":"overall","officialUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","description":{"en":"Harder successor to MMLU: about 12,000 reasoning-heavy questions in 14 disciplines with 10 answer options.","zh-hans":"MMLU 的加难版：约 1.2 万道偏推理的题，14 个学科，每题 10 个选项。"},"measures":{"en":"Knowledge plus reasoning, usually with chain-of-thought.","zh-hans":"知识加推理，通常使用思维链。"},"limitations":{"en":"The official leaderboard mixes TIGER-Lab runs with self-reported numbers; we label each row.","zh-hans":"官方榜混合了 TIGER-Lab 自测和厂商自报分数，本站逐条标注。"},"contaminationRisk":"medium","stats":{"results":247,"models":243,"latest":"2026-03-11","bySourceType":{"official":114,"vendor":133}},"sources":["mmlupro"],"pages":{"en":"https://aimap.page/en/benchmarks/mmlu-pro/","zh-hans":"https://aimap.page/zh-hans/benchmarks/mmlu-pro/"},"record":"https://aimap.page/api/benchmarks/mmlu-pro.json"},{"id":"humaneval","name":"HumanEval / HumanEval+","category":"coding","unit":"%","higherIsBetter":true,"status":"saturated","primaryVariant":"humaneval-plus","officialUrl":"https://evalplus.github.io/leaderboard.html","description":{"en":"164 hand-written Python function problems from OpenAI (2021). EvalPlus adds many more tests per problem (HumanEval+) to catch wrong solutions that pass the original tests.","zh-hans":"OpenAI 2021 年发布的 164 道 Python 函数题。EvalPlus 为每题补充大量测试（HumanEval+），能识别“通过原测试但其实是错的”答案。"},"measures":{"en":"pass@1 (greedy) on HumanEval and HumanEval+.","zh-hans":"HumanEval 与 HumanEval+ 的 pass@1（贪心解码）。"},"limitations":{"en":"Saturated and heavily contaminated; single short functions say little about real software work. EvalPlus results were last updated in December 2024.","zh-hans":"已饱和且污染严重；单个短函数说明不了真实开发能力。EvalPlus 榜单最后更新于 2024 年 12 月。"},"contaminationRisk":"high","stats":{"results":244,"models":122,"latest":"2024-12-26","bySourceType":{"official":244}},"sources":["evalplus"],"pages":{"en":"https://aimap.page/en/benchmarks/humaneval/","zh-hans":"https://aimap.page/zh-hans/benchmarks/humaneval/"},"record":"https://aimap.page/api/benchmarks/humaneval.json"},{"id":"swe-bench-verified","name":"SWE-bench Verified","category":"agent-coding","unit":"%","higherIsBetter":true,"status":"contested","primaryVariant":null,"officialUrl":"https://www.swebench.com/","description":{"en":"500 human-validated GitHub issues from 12 Python repositories; the system must produce a patch that makes the hidden tests pass.","zh-hans":"来自 12 个 Python 仓库、经人工核验的 500 个 GitHub issue，系统需生成补丁让隐藏测试通过。"},"measures":{"en":"% of issues resolved by a model + agent scaffold. Rows from swebench.com are agent systems; rows from Epoch AI use Epoch's own scaffold.","zh-hans":"模型加 agent 框架解决 issue 的比例。swebench.com 的条目是各家 agent 系统；Epoch AI 的条目用其统一框架。"},"limitations":{"en":"In February 2026 OpenAI stopped reporting SWE-bench Verified, saying it is contaminated and that 59.4% of 138 audited hard tasks had flawed tests or descriptions. Scores depend heavily on the agent scaffold.","zh-hans":"2026 年 2 月 OpenAI 宣布不再报告 SWE-bench Verified，理由是数据污染，且其审查的 138 道难题中 59.4% 的测试或描述有问题。分数也高度依赖 agent 框架。"},"contaminationRisk":"high","stats":{"results":142,"models":81,"latest":"2026-06-25","bySourceType":{"independent":33,"official":109}},"sources":["swebench","epoch"],"pages":{"en":"https://aimap.page/en/benchmarks/swe-bench-verified/","zh-hans":"https://aimap.page/zh-hans/benchmarks/swe-bench-verified/"},"record":"https://aimap.page/api/benchmarks/swe-bench-verified.json"},{"id":"swe-bench-pro","name":"SWE-bench Pro","category":"agent-coding","unit":"%","higherIsBetter":true,"status":"link-only","primaryVariant":null,"officialUrl":"https://scale.com/leaderboard/swe_bench_pro_public","description":{"en":"Scale AI's harder, longer-horizon successor to SWE-bench with a 731-task public split and private/commercial splits.","zh-hans":"Scale AI 推出的更难、更长流程的 SWE-bench 后继版本，公开集 731 题，另有私有/商业子集。"},"measures":{"en":"% of tasks resolved.","zh-hans":"任务解决率。"},"limitations":{"en":"Not collected (no open data file). OpenAI first recommended it in place of Verified, then retracted the recommendation after estimating that about 30% of Pro tasks are broken.","zh-hans":"本站未采集（没有开放数据文件）。OpenAI 先推荐用它替代 Verified，之后估计约 30% 的题目有问题，又撤回了推荐。"},"contaminationRisk":"medium","stats":{"results":0,"models":0,"latest":null,"bySourceType":{}},"sources":["scale"],"pages":{"en":"https://aimap.page/en/benchmarks/swe-bench-pro/","zh-hans":"https://aimap.page/zh-hans/benchmarks/swe-bench-pro/"},"record":null},{"id":"aime","name":"AIME (OTIS Mock AIME 2024–2025)","category":"math","unit":"%","higherIsBetter":true,"status":"active","primaryVariant":"epoch","officialUrl":"https://epoch.ai/benchmarks/otis-mock-aime","description":{"en":"AIME-style competition maths (integer answers 0–999). We use Epoch AI's runs on the OTIS Mock AIME 2024–2025 papers, which are less exposed than past official AIME papers.","zh-hans":"AIME 风格的竞赛数学（答案为 0–999 的整数）。本站使用 Epoch AI 在 OTIS 模拟 AIME 2024–2025 试卷上的评测，比历年 AIME 真题暴露更少。"},"measures":{"en":"Accuracy, averaged over runs.","zh-hans":"多次运行的平均准确率。"},"limitations":{"en":"Few questions, so results are noisy. Vendor 'AIME 2025' claims in launch posts are not comparable with these numbers.","zh-hans":"题量少，结果波动大。厂商发布会上的“AIME 2025”成绩与这里不可直接比较。"},"contaminationRisk":"medium","stats":{"results":265,"models":200,"latest":"2026-10-19","bySourceType":{"independent":265}},"sources":["epoch"],"pages":{"en":"https://aimap.page/en/benchmarks/aime/","zh-hans":"https://aimap.page/zh-hans/benchmarks/aime/"},"record":"https://aimap.page/api/benchmarks/aime.json"},{"id":"math-level-5","name":"MATH Level 5","category":"math","unit":"%","higherIsBetter":true,"status":"saturated","primaryVariant":"epoch","officialUrl":"https://github.com/hendrycks/math","description":{"en":"The hardest (level 5) problems of the MATH competition dataset (Hendrycks et al., 2021).","zh-hans":"MATH 竞赛数据集（Hendrycks 等，2021）中最难的第 5 级题目。"},"measures":{"en":"Accuracy, Epoch AI's own runs.","zh-hans":"准确率，Epoch AI 统一评测。"},"limitations":{"en":"Near saturation for reasoning models.","zh-hans":"推理模型已接近满分。"},"contaminationRisk":"high","stats":{"results":104,"models":94,"latest":"2025-10-30","bySourceType":{"independent":104}},"sources":["epoch"],"pages":{"en":"https://aimap.page/en/benchmarks/math-level-5/","zh-hans":"https://aimap.page/zh-hans/benchmarks/math-level-5/"},"record":"https://aimap.page/api/benchmarks/math-level-5.json"},{"id":"hle","name":"Humanity's Last Exam","category":"knowledge","unit":"%","higherIsBetter":true,"status":"active","primaryVariant":null,"officialUrl":"https://lastexam.ai/","description":{"en":"About 2,500 expert-written questions across 100+ subjects from the Center for AI Safety and Scale AI, filtered to stump frontier models at creation time.","zh-hans":"由 Center for AI Safety 和 Scale AI 组织、约 2500 道专家出题，覆盖 100 多个学科，出题时专门筛掉了前沿模型能答对的题。"},"measures":{"en":"Accuracy (mostly exact-match answers). Data compiled by Epoch AI.","zh-hans":"准确率（以精确匹配为主）。数据由 Epoch AI 汇编。"},"limitations":{"en":"Independent audits reported incorrect reference answers in some subjects; settings (tools, text-only) differ between reports.","zh-hans":"独立审查发现部分学科的标准答案有误；不同报告的设定（是否用工具、是否只做文本题）不同。"},"contaminationRisk":"low","stats":{"results":51,"models":46,"latest":"2026-10-07","bySourceType":{"compiled":51}},"sources":["epoch"],"pages":{"en":"https://aimap.page/en/benchmarks/hle/","zh-hans":"https://aimap.page/zh-hans/benchmarks/hle/"},"record":"https://aimap.page/api/benchmarks/hle.json"},{"id":"arc-agi-1","name":"ARC-AGI-1","category":"reasoning","unit":"%","higherIsBetter":true,"status":"saturated","primaryVariant":"semi-private","officialUrl":"https://arcprize.org/leaderboard","description":{"en":"Abstract grid puzzles (François Chollet) that test learning a new rule from a few examples.","zh-hans":"François Chollet 设计的抽象方格谜题，考察从少量示例中学会新规则的能力。"},"measures":{"en":"% of tasks solved on the semi-private set, together with cost per task.","zh-hans":"半私有题集的解题率，同时报告每题成本。"},"limitations":{"en":"ARC Prize terms restrict reproduction, so only the top entries are cited here. Cost matters: compare at similar cost per task.","zh-hans":"ARC Prize 条款限制转载，本站只引用前几名。成本很关键，应在相近的每题成本下比较。"},"contaminationRisk":"low","stats":{"results":10,"models":6,"latest":"2026-10-22","bySourceType":{"official":10}},"sources":["arcprize"],"pages":{"en":"https://aimap.page/en/benchmarks/arc-agi-1/","zh-hans":"https://aimap.page/zh-hans/benchmarks/arc-agi-1/"},"record":"https://aimap.page/api/benchmarks/arc-agi-1.json"},{"id":"arc-agi-2","name":"ARC-AGI-2","category":"reasoning","unit":"%","higherIsBetter":true,"status":"active","primaryVariant":"semi-private","officialUrl":"https://arcprize.org/leaderboard","description":{"en":"Harder second version of ARC-AGI (2025), designed so that brute-force search is not enough.","zh-hans":"ARC-AGI 第二版（2025），更难，单靠暴力搜索无法解出。"},"measures":{"en":"% solved on the semi-private set, with cost per task.","zh-hans":"半私有题集解题率及每题成本。"},"limitations":{"en":"Only the top entries are cited (terms). Systems with large test-time compute can buy accuracy with money.","zh-hans":"按条款只引用前几名。大算力推理系统可以用钱换分数。"},"contaminationRisk":"low","stats":{"results":10,"models":4,"latest":"2026-10-22","bySourceType":{"official":10}},"sources":["arcprize"],"pages":{"en":"https://aimap.page/en/benchmarks/arc-agi-2/","zh-hans":"https://aimap.page/zh-hans/benchmarks/arc-agi-2/"},"record":"https://aimap.page/api/benchmarks/arc-agi-2.json"},{"id":"arc-agi-3","name":"ARC-AGI-3","category":"reasoning","unit":"%","higherIsBetter":true,"status":"active","primaryVariant":"semi-private","officialUrl":"https://arcprize.org/leaderboard","description":{"en":"Interactive, game-like third version of ARC-AGI that tests exploration and learning inside novel environments.","zh-hans":"ARC-AGI 第三版，交互式小游戏，考察在陌生环境中探索和学习的能力。"},"measures":{"en":"Score on the semi-private set as published by ARC Prize.","zh-hans":"ARC Prize 公布的半私有题集得分。"},"limitations":{"en":"New benchmark; only the top entries are cited (terms).","zh-hans":"新基准；按条款只引用前几名。"},"contaminationRisk":"low","stats":{"results":3,"models":3,"latest":"2026-10-22","bySourceType":{"official":3}},"sources":["arcprize"],"pages":{"en":"https://aimap.page/en/benchmarks/arc-agi-3/","zh-hans":"https://aimap.page/zh-hans/benchmarks/arc-agi-3/"},"record":"https://aimap.page/api/benchmarks/arc-agi-3.json"},{"id":"osworld","name":"OSWorld (Verified)","category":"agent-computer","unit":"%","higherIsBetter":true,"status":"active","primaryVariant":null,"officialUrl":"https://os-world.github.io/","description":{"en":"369 real computer tasks in a full Ubuntu desktop (browsers, office apps, file manager, terminal) checked by execution-based scripts.","zh-hans":"在完整 Ubuntu 桌面里完成 369 个真实电脑任务（浏览器、办公软件、文件管理、终端），由脚本按执行结果判分。"},"measures":{"en":"Task success rate of computer-use agents. Data compiled by Epoch AI from the OSWorld site.","zh-hans":"电脑操作 agent 的任务成功率。数据由 Epoch AI 从 OSWorld 官网汇编。"},"limitations":{"en":"Step budgets (15/50/100) and agent frameworks differ between rows; compare like with like.","zh-hans":"各条目的步数上限（15/50/100）和 agent 框架不同，应同条件比较。"},"contaminationRisk":"medium","stats":{"results":20,"models":9,"latest":"2026-02-17","bySourceType":{"vendor":1,"official":19}},"sources":["epoch"],"pages":{"en":"https://aimap.page/en/benchmarks/osworld/","zh-hans":"https://aimap.page/zh-hans/benchmarks/osworld/"},"record":"https://aimap.page/api/benchmarks/osworld.json"},{"id":"osworld-2","name":"OSWorld 2.0","category":"agent-computer","unit":"%","higherIsBetter":true,"status":"active","primaryVariant":null,"officialUrl":"https://osworld-v2.xlang.ai/","description":{"en":"Long-horizon successor to OSWorld (2026) with multi-application workflows.","zh-hans":"OSWorld 的长流程后继版本（2026），任务跨多个应用。"},"measures":{"en":"Binary task success (partial credit reported separately).","zh-hans":"任务完全成功率（部分得分另计）。"},"limitations":{"en":"Few systems evaluated so far; expensive to run.","zh-hans":"目前评测过的系统还少，运行成本高。"},"contaminationRisk":"low","stats":{"results":14,"models":9,"latest":"2026-07-24","bySourceType":{"official":14}},"sources":["epoch"],"pages":{"en":"https://aimap.page/en/benchmarks/osworld-2/","zh-hans":"https://aimap.page/zh-hans/benchmarks/osworld-2/"},"record":"https://aimap.page/api/benchmarks/osworld-2.json"},{"id":"tau2-bench","name":"τ²-bench","category":"agent-tool","unit":"%","higherIsBetter":true,"status":"active","primaryVariant":"retail","officialUrl":"https://taubench.com/","description":{"en":"Sierra's customer-service agent benchmark: the agent follows a policy and uses tools while an LLM-simulated user talks to it (retail, airline, telecom, banking).","zh-hans":"Sierra 的客服 agent 基准：agent 要遵守业务规则并调用工具，对面是由大模型模拟的用户（零售、航空、电信、银行）。"},"measures":{"en":"pass^1 per domain (pass^k in the source measures reliability over k repeats).","zh-hans":"各领域 pass^1（来源中的 pass^k 衡量重复 k 次都成功的可靠性）。"},"limitations":{"en":"Many rows are submitted by the model developer (labelled 'vendor'); prompt addenda and user-simulator model differ.","zh-hans":"不少条目由模型厂商自己提交（标为“厂商自报”）；提示补充和模拟用户所用模型各不相同。"},"contaminationRisk":"medium","stats":{"results":100,"models":43,"latest":"2026-08-03","bySourceType":{"official":72,"vendor":28}},"sources":["tau2"],"pages":{"en":"https://aimap.page/en/benchmarks/tau2-bench/","zh-hans":"https://aimap.page/zh-hans/benchmarks/tau2-bench/"},"record":"https://aimap.page/api/benchmarks/tau2-bench.json"},{"id":"terminal-bench","name":"Terminal-Bench 2.0","category":"agent-coding","unit":"%","higherIsBetter":true,"status":"active","primaryVariant":null,"officialUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0","description":{"en":"Hard, realistic tasks an agent must finish in a sandboxed terminal (Stanford × Laude Institute).","zh-hans":"agent 需在沙箱终端里完成的高难度真实任务（斯坦福 × Laude Institute）。"},"measures":{"en":"Task accuracy for an agent + model pair. Data compiled by Epoch AI from tbench.ai.","zh-hans":"agent 与模型组合的任务正确率。数据由 Epoch AI 从 tbench.ai 汇编。"},"limitations":{"en":"Agent harness matters as much as the model; the same model appears several times with different agents.","zh-hans":"agent 框架和模型同样重要，同一模型会搭配不同 agent 多次出现。"},"contaminationRisk":"low","stats":{"results":202,"models":45,"latest":"2026-05-14","bySourceType":{"compiled":5,"official":197}},"sources":["epoch"],"pages":{"en":"https://aimap.page/en/benchmarks/terminal-bench/","zh-hans":"https://aimap.page/zh-hans/benchmarks/terminal-bench/"},"record":"https://aimap.page/api/benchmarks/terminal-bench.json"},{"id":"bfcl","name":"BFCL v4 (function calling)","category":"agent-tool","unit":"%","higherIsBetter":true,"status":"active","primaryVariant":"overall","officialUrl":"https://gorilla.cs.berkeley.edu/leaderboard.html","description":{"en":"Berkeley Function Calling Leaderboard: single, parallel and multi-turn tool calls, web search, memory and relevance detection.","zh-hans":"伯克利函数调用排行榜：单次/并行/多轮工具调用、网页搜索、记忆、判断该不该调用工具。"},"measures":{"en":"Overall accuracy across categories; FC = native function calling, Prompt = tool calls via prompting.","zh-hans":"各类别综合正确率；FC 表示原生函数调用，Prompt 表示用提示词实现调用。"},"limitations":{"en":"AST matching can mark valid alternative calls as wrong; leaderboard updates are periodic.","zh-hans":"按语法树比对，可能把合理的其他调用方式判错；榜单定期而非实时更新。"},"contaminationRisk":"medium","stats":{"results":107,"models":80,"latest":"2026-10-17","bySourceType":{"official":107}},"sources":["bfcl"],"pages":{"en":"https://aimap.page/en/benchmarks/bfcl/","zh-hans":"https://aimap.page/zh-hans/benchmarks/bfcl/"},"record":"https://aimap.page/api/benchmarks/bfcl.json"},{"id":"cmmlu","name":"CMMLU","category":"chinese","unit":"%","higherIsBetter":true,"status":"stale","primaryVariant":"five-shot","officialUrl":"https://github.com/haonan-li/CMMLU","description":{"en":"Chinese multitask knowledge benchmark: 67 subjects including China-specific topics.","zh-hans":"中文多任务知识基准：67 个学科，含中国特有主题。"},"measures":{"en":"Average accuracy (five-shot / zero-shot).","zh-hans":"平均准确率（5-shot / 0-shot）。"},"limitations":{"en":"Leaderboard last updated in 2024; mostly older models; data licence is non-commercial, so only the top entries are cited.","zh-hans":"榜单最后更新于 2024 年，以旧模型为主；数据为非商业许可，本站只引用前几名。"},"contaminationRisk":"high","stats":{"results":20,"models":12,"latest":"2024-12-06","bySourceType":{"official":20}},"sources":["cmmlu"],"pages":{"en":"https://aimap.page/en/benchmarks/cmmlu/","zh-hans":"https://aimap.page/zh-hans/benchmarks/cmmlu/"},"record":"https://aimap.page/api/benchmarks/cmmlu.json"},{"id":"c-eval","name":"C-Eval","category":"chinese","unit":"%","higherIsBetter":true,"status":"stale","primaryVariant":"five-shot","officialUrl":"https://cevalbenchmark.com/static/leaderboard.html","description":{"en":"Chinese evaluation suite of about 13,900 multiple-choice questions over 52 disciplines and four difficulty levels.","zh-hans":"中文综合评测，约 1.39 万道选择题，52 个学科、四个难度等级。"},"measures":{"en":"Average accuracy. Only the initial-release table from the GitHub README is cited here.","zh-hans":"平均准确率。本站只引用 GitHub README 中首发时的表格。"},"limitations":{"en":"The live leaderboard (cevalbenchmark.com) could not be reached from our network on 2026-10-10; the README table is from 2023.","zh-hans":"2026-10-10 从本站网络无法访问实时榜单（cevalbenchmark.com）；README 表格是 2023 年的数据。"},"contaminationRisk":"high","stats":{"results":20,"models":11,"latest":"2023-05-15","bySourceType":{"official":20}},"sources":["ceval"],"pages":{"en":"https://aimap.page/en/benchmarks/c-eval/","zh-hans":"https://aimap.page/zh-hans/benchmarks/c-eval/"},"record":"https://aimap.page/api/benchmarks/c-eval.json"},{"id":"superclue","name":"SuperCLUE","category":"chinese","unit":"score","higherIsBetter":true,"status":"link-only","primaryVariant":null,"officialUrl":"https://www.superclueai.com/","description":{"en":"Periodic Chinese general-capability evaluation of domestic and international models, published as reports.","zh-hans":"定期发布的中文通用能力测评，覆盖国内外模型，以报告形式发布。"},"measures":{"en":"Composite score across Chinese tasks.","zh-hans":"中文任务综合得分。"},"limitations":{"en":"Not collected: no open data interface; questions are private, so results cannot be reproduced independently.","zh-hans":"本站未采集：没有开放数据接口；题目不公开，无法独立复现。"},"contaminationRisk":"low","stats":{"results":0,"models":0,"latest":null,"bySourceType":{}},"sources":["superclue"],"pages":{"en":"https://aimap.page/en/benchmarks/superclue/","zh-hans":"https://aimap.page/zh-hans/benchmarks/superclue/"},"record":null}],"models":[{"id":"claude-sonnet-4-5","name":"Claude Sonnet 4.5","provider":"Anthropic","openWeights":false,"release":"2025-09-29","aliases":["claude-sonnet-4-5-20250929-high-32k","claude-sonnet-4-5-20250929","claude-sonnet-4-5-20250929_16K","Claude Sonnet 4.5 (16k thinking)","claude-sonnet-4-5-20250929_59K","Claude Sonnet 4.5 (59k thinking)","claude-sonnet-4-5-20250929_32K","Claude Sonnet 4.5 (32k thinking)","Claude Sonnet 4.5 (no thinking)","claude-sonnet-4-5-20250929_unknown","Claude Sonnet 4.5 (unknown thinking)","claude-sonnet-4-5-20250929-thinking","Claude 4.5 Sonnet","claude-sonnet-4-5","Sonar Foundation Agent + Claude 4.5 Sonnet"],"page":{"en":"https://aimap.page/en/benchmarks/model/claude-sonnet-4-5/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/claude-sonnet-4-5/"},"best":{"lmarena-text":{"score":1456.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1393.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"gpqa-diamond":{"score":82.32,"unit":"%","sourceType":"independent","date":"2025-10-28","source":"https://epoch.ai/benchmarks"},"swe-bench-verified":{"score":74.8,"unit":"%","sourceType":"official","date":"2025-11-03","source":"https://www.swebench.com/#verified"},"aime":{"score":77.78,"unit":"%","sourceType":"independent","date":"2025-10-28","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":97.73,"unit":"%","sourceType":"independent","date":"2025-10-21","source":"https://epoch.ai/benchmarks"},"hle":{"score":13.72,"unit":"%","sourceType":"compiled","date":"2025-09-29","source":"https://epoch.ai/benchmarks"},"osworld":{"score":62.9,"unit":"%","sourceType":"official","date":"2025-10-30","source":"https://os-world.github.io/"},"tau2-bench":{"score":72.4,"unit":"%","sourceType":"official","date":"2026-02-24","source":"https://taubench.com/"},"terminal-bench":{"score":46.52,"unit":"%","sourceType":"official","date":"2025-09-29","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},"bfcl":{"score":73.24,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"gemini-2-5-pro-jun-2025","name":"Gemini 2.5 Pro (Jun 2025)","provider":"Google","openWeights":false,"release":"2025-06-05","aliases":["gemini-2.5-pro","gemini-2.5-pro-preview-06-05","Gemini 2.5 Pro Preview (Jun 2025)","Gemini 2.5 Pro","Gemini 2.5 Pro (2025-05-06)","Gemini-2.5-Pro-06-05","Gemini-2.5-Pro"],"page":{"en":"https://aimap.page/en/benchmarks/model/gemini-2-5-pro-jun-2025/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gemini-2-5-pro-jun-2025/"},"best":{"lmarena-text":{"score":1445.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1227.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1247.5,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"livecodebench":{"score":74.2,"unit":"%","sourceType":"official","date":"2025-04-07","source":"https://livecodebench.github.io/leaderboard.html"},"gpqa-diamond":{"score":85.29,"unit":"%","sourceType":"independent","date":"2025-11-16","source":"https://epoch.ai/benchmarks"},"mmlu-pro":{"score":86,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"swe-bench-verified":{"score":57.56,"unit":"%","sourceType":"independent","date":"2026-02-13","source":"https://epoch.ai/benchmarks"},"aime":{"score":84.72,"unit":"%","sourceType":"independent","date":"2025-11-16","source":"https://epoch.ai/benchmarks"},"hle":{"score":21.64,"unit":"%","sourceType":"compiled","date":"2025-06-05","source":"https://epoch.ai/benchmarks"},"terminal-bench":{"score":32.64,"unit":"%","sourceType":"official","date":"2025-06-17","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"}}},{"id":"gemini-3-pro","name":"Gemini 3 Pro","provider":"Google","openWeights":false,"release":"2025-11-18","aliases":["gemini-3-pro","gemini-3-pro-preview","Gemini 3 Pro Preview","live-SWE-agent + Gemini 3 Pro Preview (2025-11-18)","Gemini 3 Pro Preview (2025-11-18)","Gemini-3-Pro-Preview (Prompt)","Gemini-3-Pro-Preview (FC)","Gemini-3-Pro(11/25)"],"page":{"en":"https://aimap.page/en/benchmarks/model/gemini-3-pro/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gemini-3-pro/"},"best":{"lmarena-text":{"score":1485.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1439.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1289.3,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":92.61,"unit":"%","sourceType":"independent","date":"2025-11-19","source":"https://epoch.ai/benchmarks"},"mmlu-pro":{"score":90.1,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"swe-bench-verified":{"score":77.4,"unit":"%","sourceType":"official","date":"2025-11-20","source":"https://www.swebench.com/#verified"},"aime":{"score":91.39,"unit":"%","sourceType":"independent","date":"2025-11-19","source":"https://epoch.ai/benchmarks"},"hle":{"score":37.52,"unit":"%","sourceType":"compiled","date":"2025-11-18","source":"https://epoch.ai/benchmarks"},"tau2-bench":{"score":75.9,"unit":"%","sourceType":"official","date":"2026-03-02","source":"https://taubench.com/"},"terminal-bench":{"score":69.43,"unit":"%","sourceType":"official","date":"2025-11-18","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},"bfcl":{"score":72.51,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"gpt-5","name":"GPT-5","provider":"OpenAI","openWeights":false,"release":"2025-08-07","aliases":["gpt-5-high","gpt-5-chat","gpt-5-medium","gpt-5-2025-08-07_minimal","GPT-5 (minimal)","gpt-5-2025-08-07_high","GPT-5 (high)","gpt-5-2025-08-07_medium","GPT-5 (medium)","gpt-5-2025-08-07","gpt-5-2025-08-07_unknown","GPT-5 (unknown thinking)","Prometheus-v1.2.1 + GPT-5","openai/gpt-5-2025-08-07","OpenHands + GPT-5"],"page":{"en":"https://aimap.page/en/benchmarks/model/gpt-5/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gpt-5/"},"best":{"lmarena-text":{"score":1434.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1417.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1225.7,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":86.17,"unit":"%","sourceType":"independent","date":"2025-10-29","source":"https://epoch.ai/benchmarks"},"mmlu-pro":{"score":87.1,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"swe-bench-verified":{"score":74.4,"unit":"%","sourceType":"official","date":"2025-10-15","source":"https://www.swebench.com/#verified"},"aime":{"score":91.39,"unit":"%","sourceType":"independent","date":"2025-10-29","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":98.13,"unit":"%","sourceType":"independent","date":"2025-10-29","source":"https://epoch.ai/benchmarks"},"hle":{"score":25.32,"unit":"%","sourceType":"compiled","date":"2025-08-07","source":"https://epoch.ai/benchmarks"},"tau2-bench":{"score":81.6,"unit":"%","sourceType":"official","date":"2025-08-09","source":"https://taubench.com/"},"terminal-bench":{"score":49.61,"unit":"%","sourceType":"official","date":"2025-08-07","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"}}},{"id":"gpt-5-2","name":"GPT-5.2","provider":"OpenAI","openWeights":false,"release":"2025-12-11","aliases":["gpt-5.2-high","gpt-5.2","gpt-5.2-2025-12-11_none","GPT-5.2 (none)","gpt-5.2-2025-12-11_xhigh","GPT-5.2 (xhigh)","gpt-5.2-2025-12-11_high","GPT-5.2 (high)","gpt-5.2-2025-12-11_medium","GPT-5.2 (medium)","gpt-5.2-2025-12-11_low","GPT-5.2 (low)","gpt-5.2-2025-12-11_unknown","GPT-5.2 (unknown thinking)","gpt-5.2-2025-12-11"],"page":{"en":"https://aimap.page/en/benchmarks/model/gpt-5-2/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gpt-5-2/"},"best":{"lmarena-text":{"score":1437.2,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1416,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1242.8,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":91.4,"unit":"%","sourceType":"independent","date":"2025-12-13","source":"https://epoch.ai/benchmarks"},"mmlu-pro":{"score":87.4,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"swe-bench-verified":{"score":73.76,"unit":"%","sourceType":"independent","date":"2026-02-12","source":"https://epoch.ai/benchmarks"},"aime":{"score":96.11,"unit":"%","sourceType":"independent","date":"2025-12-11","source":"https://epoch.ai/benchmarks"},"hle":{"score":27.8,"unit":"%","sourceType":"compiled","date":"2025-12-11","source":"https://epoch.ai/benchmarks"},"tau2-bench":{"score":81.6,"unit":"%","sourceType":"official","date":"2026-05-05","source":"https://taubench.com/"},"terminal-bench":{"score":64.94,"unit":"%","sourceType":"official","date":"2025-12-11","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},"bfcl":{"score":55.87,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"o3","name":"o3","provider":"OpenAI","openWeights":false,"release":"2025-04-16","aliases":["o3-2025-04-16_medium","o3 (medium)","o3-2025-04-16_low","o3 (low)","o3-2025-04-16_high","o3 (high)","o3 (high) (April 2025)","o3 (medium) (April 2025)","o3-20250416","o3 (2025-04-16)","O3 (High)","o3__high","o3-2025-04-16 (Prompt)","o3-2025-04-16 (FC)"],"page":{"en":"https://aimap.page/en/benchmarks/model/o3/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/o3/"},"best":{"lmarena-text":{"score":1431.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1215.7,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"livecodebench":{"score":72,"unit":"%","sourceType":"official","date":"2025-04-07","source":"https://livecodebench.github.io/leaderboard.html"},"gpqa-diamond":{"score":81.82,"unit":"%","sourceType":"independent","date":"2025-04-16","source":"https://epoch.ai/benchmarks"},"swe-bench-verified":{"score":62.32,"unit":"%","sourceType":"independent","date":"2026-02-12","source":"https://epoch.ai/benchmarks"},"aime":{"score":84.44,"unit":"%","sourceType":"independent","date":"2026-08-07","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":97.77,"unit":"%","sourceType":"independent","date":"2025-04-16","source":"https://epoch.ai/benchmarks"},"hle":{"score":20.32,"unit":"%","sourceType":"compiled","date":"2025-04-16","source":"https://epoch.ai/benchmarks"},"osworld":{"score":23,"unit":"%","sourceType":"official","date":"2025-07-27","source":"https://os-world.github.io/"},"tau2-bench":{"score":73.9,"unit":"%","sourceType":"vendor","date":"2025-04-16","source":"https://openai.com/index/introducing-o3-and-o4-mini/"},"bfcl":{"score":63.05,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"claude-3-7-sonnet","name":"Claude 3.7 Sonnet","provider":"Anthropic","openWeights":false,"release":"2025-02-24","aliases":["claude-3-7-sonnet-20250219-thinking-32k","claude-3-7-sonnet-20250219","claude-3-7-sonnet-20250219_64K","Claude 3.7 Sonnet (64k thinking)","claude-3-7-sonnet-20250219_32K","Claude 3.7 Sonnet (32k thinking)","claude-3-7-sonnet-20250219_16K","Claude 3.7 Sonnet (16k thinking)","claude-3-7-sonnet-20250219_unknown","Claude 3.7 Sonnet (unknown thinking)","Claude 3.7 Sonnet (Thinking)","Aime-coder v1 + Anthopic Claude 3.7 Sonnet","Claude 3.7 Sonnet w/ Review Heavy","SWE-agent + Claude 3.7 Sonnet w/ Review Heavy","Claude 3.7 Sonnet (20250219)"],"page":{"en":"https://aimap.page/en/benchmarks/model/claude-3-7-sonnet/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/claude-3-7-sonnet/"},"best":{"lmarena-text":{"score":1388.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1192.8,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":79.73,"unit":"%","sourceType":"independent","date":"2025-05-26","source":"https://epoch.ai/benchmarks"},"mmlu-pro":{"score":84,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"swe-bench-verified":{"score":66.4,"unit":"%","sourceType":"official","date":"2025-05-14","source":"https://www.swebench.com/#verified"},"aime":{"score":57.78,"unit":"%","sourceType":"independent","date":"2025-03-13","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":91.16,"unit":"%","sourceType":"independent","date":"2025-03-13","source":"https://epoch.ai/benchmarks"},"hle":{"score":8.04,"unit":"%","sourceType":"compiled","date":"2025-02-24","source":"https://epoch.ai/benchmarks"},"osworld":{"score":35.8,"unit":"%","sourceType":"official","date":"2025-07-27","source":"https://os-world.github.io/"},"tau2-bench":{"score":72.1,"unit":"%","sourceType":"official","date":"2025-06-09","source":"https://taubench.com/"}}},{"id":"claude-opus-4-5","name":"Claude Opus 4.5","provider":"Anthropic","openWeights":false,"release":"2025-11-24","aliases":["claude-opus-4-5-20251101-high-32k","claude-opus-4-5-20251101","claude-opus-4-5-20251101_16K","Claude Opus 4.5 (16k thinking)","claude-opus-4-5-20251101_32K","Claude Opus 4.5 (32k thinking)","Claude Opus 4.5 (no thinking)","claude-opus-4-5-20251101_unknown","Claude Opus 4.5 (unknown thinking)","claude-opus-4-5-20251101-thinking","claude-opus-4-5-20251101_128K","Claude Opus 4.5 (128k thinking)","claude-opus-4-5","Claude 4.5 Opus","Sonar Foundation Agent + Claude 4.5 Opus"],"page":{"en":"https://aimap.page/en/benchmarks/model/claude-opus-4-5/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/claude-opus-4-5/"},"best":{"lmarena-text":{"score":1473.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1493.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"gpqa-diamond":{"score":86.05,"unit":"%","sourceType":"independent","date":"2025-11-24","source":"https://epoch.ai/benchmarks"},"swe-bench-verified":{"score":79.2,"unit":"%","sourceType":"official","date":"2025-12-05","source":"https://www.swebench.com/#verified"},"aime":{"score":86.11,"unit":"%","sourceType":"independent","date":"2025-11-24","source":"https://epoch.ai/benchmarks"},"hle":{"score":25.2,"unit":"%","sourceType":"compiled","date":"2025-11-24","source":"https://epoch.ai/benchmarks"},"osworld":{"score":66.3,"unit":"%","sourceType":"vendor","date":"2025-11-25","source":"https://www.anthropic.com/news/claude-opus-4-5"},"tau2-bench":{"score":79.6,"unit":"%","sourceType":"official","date":"2026-05-05","source":"https://taubench.com/"},"terminal-bench":{"score":63.15,"unit":"%","sourceType":"official","date":"2025-11-24","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},"bfcl":{"score":77.47,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"claude-opus-4-7","name":"Claude Opus 4.7","provider":"Anthropic","openWeights":false,"release":"2026-04-16","aliases":["claude-opus-4-7-high","claude-opus-4-7","claude-opus-4-7_max","Claude Opus 4.7 (max)","claude-opus-4-7_xhigh","Claude Opus 4.7 (xhigh)","claude-opus-4-7_unknown","Claude Opus 4.7 (unknown)"],"page":{"en":"https://aimap.page/en/benchmarks/model/claude-opus-4-7/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/claude-opus-4-7/"},"best":{"lmarena-text":{"score":1501,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1557.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1298.1,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":90.15,"unit":"%","sourceType":"independent","date":"2026-04-17","source":"https://epoch.ai/benchmarks"},"swe-bench-verified":{"score":83.47,"unit":"%","sourceType":"independent","date":"2026-04-20","source":"https://epoch.ai/benchmarks"},"aime":{"score":97.8,"unit":"%","sourceType":"independent","date":"2026-04-17","source":"https://epoch.ai/benchmarks"},"hle":{"score":36.2,"unit":"%","sourceType":"compiled","date":"2026-04-16","source":"https://epoch.ai/benchmarks"},"osworld-2":{"score":18.2,"unit":"%","sourceType":"official","date":"2026-04-16","source":"https://osworld-v2.xlang.ai/"},"terminal-bench":{"score":80.22,"unit":"%","sourceType":"official","date":"2026-04-16","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"}}},{"id":"claude-sonnet-4","name":"Claude Sonnet 4","provider":"Anthropic","openWeights":false,"release":"2025-05-22","aliases":["claude-sonnet-4-20250514-thinking-32k","claude-sonnet-4-20250514","claude-sonnet-4-20250514_59K","claude-sonnet-4-20250514_32K","claude-sonnet-4-20250514_16K","claude-sonnet-4-20250514_unknown","Claude Sonnet 4 (unknown thinking)","Claude Sonnet 4 (Thinking)","Claude 4 Sonnet","EPAM AI/Run Developer Agent v20250719 + Claude 4 Sonnet","Harness AI","Artemis Agent v2 (2025-09-24)","Claude-Sonnet-4 (Thinking)","Claude-Sonnet-4","claude-sonnet-4-20250514_nothink"],"page":{"en":"https://aimap.page/en/benchmarks/model/claude-sonnet-4/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/claude-sonnet-4/"},"best":{"lmarena-text":{"score":1401.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1206.2,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"livecodebench":{"score":48.9,"unit":"%","sourceType":"official","date":"2025-04-07","source":"https://livecodebench.github.io/leaderboard.html"},"gpqa-diamond":{"score":79.19,"unit":"%","sourceType":"independent","date":"2025-05-26","source":"https://epoch.ai/benchmarks"},"swe-bench-verified":{"score":76.8,"unit":"%","sourceType":"official","date":"2025-08-04","source":"https://www.swebench.com/#verified"},"aime":{"score":68.89,"unit":"%","sourceType":"independent","date":"2025-05-23","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":84.37,"unit":"%","sourceType":"independent","date":"2025-05-22","source":"https://epoch.ai/benchmarks"},"hle":{"score":7.76,"unit":"%","sourceType":"compiled","date":"2025-05-22","source":"https://epoch.ai/benchmarks"},"osworld":{"score":43.9,"unit":"%","sourceType":"official","date":"2025-07-27","source":"https://os-world.github.io/"},"tau2-bench":{"score":80.5,"unit":"%","sourceType":"vendor","date":"2025-05-22","source":"https://www.anthropic.com/news/claude-4"}}},{"id":"gemini-3-1-pro","name":"Gemini 3.1 Pro","provider":"Google","openWeights":false,"release":"2026-02-19","aliases":["gemini-3.1-pro-preview","gemini-3.1-pro-preview_high","Gemini 3.1 Pro Preview","gemini-3.1-pro-preview-customtools","Gemini 3.1 Pro Preview (thinking high)","Gemini-3.1-Pro","Gemini 3.1 Pro (Preview)"],"page":{"en":"https://aimap.page/en/benchmarks/model/gemini-3-1-pro/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gemini-3-1-pro/"},"best":{"lmarena-text":{"score":1487.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1446.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1279.3,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":94.44,"unit":"%","sourceType":"independent","date":"2026-08-06","source":"https://epoch.ai/benchmarks"},"mmlu-pro":{"score":91.16,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"swe-bench-verified":{"score":75.62,"unit":"%","sourceType":"independent","date":"2026-02-24","source":"https://epoch.ai/benchmarks"},"aime":{"score":95.56,"unit":"%","sourceType":"independent","date":"2026-08-06","source":"https://epoch.ai/benchmarks"},"hle":{"score":46.44,"unit":"%","sourceType":"compiled","date":"2026-02-19","source":"https://epoch.ai/benchmarks"},"terminal-bench":{"score":80.22,"unit":"%","sourceType":"official","date":"2026-02-19","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"}}},{"id":"gpt-4-1","name":"GPT-4.1","provider":"OpenAI","openWeights":false,"release":"2025-04-14","aliases":["gpt-4.1-2025-04-14","gpt-4.1-20250414","GPT 4.1","GPT 4.1 (2025-04-14)","GPT-4.1-2025-04-14 (FC)","GPT-4.1-2025-04-14 (Prompt)"],"page":{"en":"https://aimap.page/en/benchmarks/model/gpt-4-1/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gpt-4-1/"},"best":{"lmarena-text":{"score":1414.6,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1214,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":66.92,"unit":"%","sourceType":"independent","date":"2025-04-14","source":"https://epoch.ai/benchmarks"},"mmlu-pro":{"score":81.8,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"swe-bench-verified":{"score":48.54,"unit":"%","sourceType":"independent","date":"2026-02-08","source":"https://epoch.ai/benchmarks"},"aime":{"score":38.33,"unit":"%","sourceType":"independent","date":"2025-04-14","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":83.01,"unit":"%","sourceType":"independent","date":"2025-04-14","source":"https://epoch.ai/benchmarks"},"hle":{"score":5.4,"unit":"%","sourceType":"compiled","date":"2025-04-14","source":"https://epoch.ai/benchmarks"},"tau2-bench":{"score":74,"unit":"%","sourceType":"official","date":"2025-06-09","source":"https://taubench.com/"},"bfcl":{"score":53.96,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"gpt-5-4","name":"GPT-5.4","provider":"OpenAI","openWeights":false,"release":"2026-03-05","aliases":["gpt-5.4-high","gpt-5.4","gpt-5.4-2026-03-05_medium","GPT-5.4 (medium)","gpt-5.4-2026-03-05_none","GPT-5.4 (none)","gpt-5.4-2026-03-05_high","GPT-5.4 (high)","gpt-5.4-2026-03-05_low","GPT-5.4 (low)","gpt-5.4-2026-03-05_xhigh","GPT-5.4 (xhigh)","gpt-5.4-2026-03-05 (xhigh thinking)","gpt-5.4-2026-03-05_unknown","GPT-5.4 (unknown thinking)"],"page":{"en":"https://aimap.page/en/benchmarks/model/gpt-5-4/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gpt-5-4/"},"best":{"lmarena-text":{"score":1475.2,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1400.2,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1283.8,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":93.3,"unit":"%","sourceType":"independent","date":"2026-03-06","source":"https://epoch.ai/benchmarks"},"mmlu-pro":{"score":87.5,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"swe-bench-verified":{"score":76.86,"unit":"%","sourceType":"independent","date":"2026-03-06","source":"https://epoch.ai/benchmarks"},"aime":{"score":97.78,"unit":"%","sourceType":"independent","date":"2026-07-15","source":"https://epoch.ai/benchmarks"},"hle":{"score":36.24,"unit":"%","sourceType":"compiled","date":"2026-03-05","source":"https://epoch.ai/benchmarks"},"terminal-bench":{"score":81.8,"unit":"%","sourceType":"official","date":"2026-03-12","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"}}},{"id":"o4-mini","name":"o4-mini","provider":"OpenAI","openWeights":false,"release":"2025-04-16","aliases":["o4-mini-2025-04-16_medium","o4-mini (medium)","o4-mini-2025-04-16_low","o4-mini (low)","o4-mini-2025-04-16_high","o4-mini (high)","o4-mini (high) (April 2025)","o4-mini (medium) (April 2025)","PatchPilot-v1.1","o4-mini-20250416","o4-mini (2025-04-16)","O4-Mini (High)","o4-mini__high","O4-Mini (Medium)","o4-mini-2025-04-16 (FC)"],"page":{"en":"https://aimap.page/en/benchmarks/model/o4-mini/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/o4-mini/"},"best":{"lmarena-text":{"score":1390.9,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1200.8,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"livecodebench":{"score":75.8,"unit":"%","sourceType":"official","date":"2025-04-07","source":"https://livecodebench.github.io/leaderboard.html"},"gpqa-diamond":{"score":79.61,"unit":"%","sourceType":"independent","date":"2025-04-16","source":"https://epoch.ai/benchmarks"},"swe-bench-verified":{"score":64.6,"unit":"%","sourceType":"official","date":"2025-05-03","source":"https://www.swebench.com/#verified"},"aime":{"score":81.67,"unit":"%","sourceType":"independent","date":"2025-04-16","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":97.83,"unit":"%","sourceType":"independent","date":"2025-04-16","source":"https://epoch.ai/benchmarks"},"hle":{"score":18.08,"unit":"%","sourceType":"compiled","date":"2025-04-16","source":"https://epoch.ai/benchmarks"},"tau2-bench":{"score":68.3,"unit":"%","sourceType":"official","date":"2025-06-09","source":"https://taubench.com/"},"bfcl":{"score":53.24,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"qwen2-5-72b","name":"Qwen2.5-72B","provider":"Alibaba (Qwen)","openWeights":true,"release":"2024-09-19","aliases":["qwen2.5-72b-instruct","qwen2.5-vl-72b-instruct","Qwen2.5 72B Base","Qwen2.5 72b instruct","Qwen2.5 Instruct Turbo (72B)","Qwen2.5-VL-72B-Instruct","Qwen/Qwen2.5-72B-Instruct","Qwen/Qwen2.5-72B"],"page":{"en":"https://aimap.page/en/benchmarks/model/qwen2-5-72b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/qwen2-5-72b/"},"best":{"lmarena-text":{"score":1302.9,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1121.2,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"open-llm-leaderboard":{"score":47.98,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"gpqa-diamond":{"score":49.15,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":83.4,"unit":"%","sourceType":"official","date":"2024-09-19","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"mmlu-pro":{"score":71.59,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"aime":{"score":8.06,"unit":"%","sourceType":"independent","date":"2025-02-25","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":63.17,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"osworld":{"score":5,"unit":"%","sourceType":"official","date":"2025-07-27","source":"https://os-world.github.io/"},"cmmlu":{"score":85.67,"unit":"%","sourceType":"official","date":"2024-12-06","source":"https://github.com/haonan-li/CMMLU#排行榜"}}},{"id":"claude-3-haiku","name":"Claude 3 Haiku","provider":"Anthropic","openWeights":false,"release":"2024-03-07","aliases":["claude-3-haiku-20240307","Claude 3 Haiku (20240307)","Claude 3.5 Haiku","Tools + Claude 3.5 Haiku","Claude-3-Haiku","Claude-3-Haiku-20240307"],"page":{"en":"https://aimap.page/en/benchmarks/model/claude-3-haiku/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/claude-3-haiku/"},"best":{"lmarena-text":{"score":1261.6,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1000,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"livecodebench":{"score":23.9,"unit":"%","sourceType":"official","date":"2025-04-07","source":"https://livecodebench.github.io/leaderboard.html"},"gpqa-diamond":{"score":36.3,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":73.8,"unit":"%","sourceType":"official","date":"2024-03-07","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"mmlu-pro":{"score":42.29,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"swe-bench-verified":{"score":40.6,"unit":"%","sourceType":"official","date":"2024-10-22","source":"https://www.swebench.com/#verified"},"aime":{"score":1.81,"unit":"%","sourceType":"independent","date":"2025-02-25","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":14.88,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"}}},{"id":"claude-3-5-sonnet","name":"Claude 3.5 Sonnet","provider":"Anthropic","openWeights":false,"release":"2024-06-20","aliases":["claude-3-5-sonnet-20241022","claude-3-5-sonnet-20240620","Claude 3.5 Sonnet (Jun 2024)","Claude 3.5 Sonnet (20240620)","AgentScope","EPAM AI/Run Developer Agent v20250219 + Anthopic Claude 3.5 Sonnet","swe-search","CodeStory Midwit Agent + swe-search","Learn-by-interact","EPAM AI/Run Developer Agent v20241212 + Anthopic Claude 3.5 Sonnet","devlo","Engine Labs (2024-11-25)","Claude 3.5-Sonnet-20241022","AutoCodeRover-v2.1 (Claude-3.5-Sonnet-20241022)","Agentless-1.5 + Claude-3.5 Sonnet (20241022)"],"page":{"en":"https://aimap.page/en/benchmarks/model/claude-3-5-sonnet/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/claude-3-5-sonnet/"},"best":{"lmarena-text":{"score":1374.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1160.7,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"livecodebench":{"score":34.8,"unit":"%","sourceType":"official","date":"2025-04-07","source":"https://livecodebench.github.io/leaderboard.html"},"gpqa-diamond":{"score":54.04,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":86.5,"unit":"%","sourceType":"official","date":"2024-06-20","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"mmlu-pro":{"score":77.64,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"swe-bench-verified":{"score":63.4,"unit":"%","sourceType":"official","date":"2025-02-06","source":"https://www.swebench.com/#verified"},"aime":{"score":6.53,"unit":"%","sourceType":"independent","date":"2025-02-25","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":51.68,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"}}},{"id":"claude-opus-4","name":"Claude Opus 4","provider":"Anthropic","openWeights":false,"release":"2025-05-22","aliases":["claude-opus-4-20250514-thinking-16k","claude-opus-4-20250514","claude-opus-4-20250514_16K","claude-opus-4-20250514_27K","claude-opus-4-20250514_unknown","Claude Opus 4 (Thinking)","Claude-Opus-4 (Thinking)","Claude-Opus-4","claude-opus-4-20250514_nothink"],"page":{"en":"https://aimap.page/en/benchmarks/model/claude-opus-4/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/claude-opus-4/"},"best":{"lmarena-text":{"score":1426.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1207.4,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"livecodebench":{"score":51.1,"unit":"%","sourceType":"official","date":"2025-04-07","source":"https://livecodebench.github.io/leaderboard.html"},"gpqa-diamond":{"score":76.26,"unit":"%","sourceType":"independent","date":"2025-05-22","source":"https://epoch.ai/benchmarks"},"swe-bench-verified":{"score":70.66,"unit":"%","sourceType":"independent","date":"2026-02-06","source":"https://epoch.ai/benchmarks"},"aime":{"score":64.44,"unit":"%","sourceType":"independent","date":"2025-05-28","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":85.05,"unit":"%","sourceType":"independent","date":"2025-05-22","source":"https://epoch.ai/benchmarks"},"hle":{"score":10.72,"unit":"%","sourceType":"compiled","date":"2025-05-22","source":"https://epoch.ai/benchmarks"},"tau2-bench":{"score":81.4,"unit":"%","sourceType":"vendor","date":"2025-05-22","source":"https://www.anthropic.com/news/claude-4"}}},{"id":"claude-opus-4-6","name":"Claude Opus 4.6","provider":"Anthropic","openWeights":false,"release":"2026-02-05","aliases":["claude-opus-4-6-high","claude-opus-4-6","claude-opus-4-6_max","Claude Opus 4.6 (max)","claude-opus-4-6_32K","Claude Opus 4.6 (32k thinking)","claude-opus-4-6_64K","Claude Opus 4.6 (64k thinking)","Claude Opus 4.6 (no thinking)","claude-opus-4-6-thinking-max","claude-opus-4-6 (Non-Thinking)","claude-opus-4-6_unknown","Claude Opus 4.6 (unknown thinking)","Claude 4.6 Opus"],"page":{"en":"https://aimap.page/en/benchmarks/model/claude-opus-4-6/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/claude-opus-4-6/"},"best":{"lmarena-text":{"score":1504.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1546.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1299.4,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":90.53,"unit":"%","sourceType":"independent","date":"2026-02-06","source":"https://epoch.ai/benchmarks"},"swe-bench-verified":{"score":78.72,"unit":"%","sourceType":"independent","date":"2026-02-18","source":"https://epoch.ai/benchmarks"},"aime":{"score":94.44,"unit":"%","sourceType":"independent","date":"2026-02-06","source":"https://epoch.ai/benchmarks"},"hle":{"score":34.44,"unit":"%","sourceType":"compiled","date":"2026-02-05","source":"https://epoch.ai/benchmarks"},"terminal-bench":{"score":79.8,"unit":"%","sourceType":"official","date":"2026-03-12","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"}}},{"id":"claude-sonnet-4-6","name":"Claude Sonnet 4.6","provider":"Anthropic","openWeights":false,"release":"2026-02-17","aliases":["claude-sonnet-4-6","claude-sonnet-4-6_max","Claude Sonnet 4.6 (max)","claude-sonnet-4-6_high","Claude Sonnet 4.6 (high)","claude-sonnet-4-6_medium","Claude Sonnet 4.6 (medium)","claude-sonnet-4-6_32K","Claude Sonnet 4.6 (32k thinking)","Claude Sonnet 4.6 (no thinking)","claude-sonnet-4-6_unknown","Claude Sonnet 4.6 (unknown thinking)"],"page":{"en":"https://aimap.page/en/benchmarks/model/claude-sonnet-4-6/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/claude-sonnet-4-6/"},"best":{"lmarena-text":{"score":1472,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1522.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1275.2,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":87.37,"unit":"%","sourceType":"independent","date":"2026-02-20","source":"https://epoch.ai/benchmarks"},"swe-bench-verified":{"score":75.21,"unit":"%","sourceType":"independent","date":"2026-02-21","source":"https://epoch.ai/benchmarks"},"aime":{"score":85.79,"unit":"%","sourceType":"independent","date":"2026-02-20","source":"https://epoch.ai/benchmarks"},"osworld":{"score":72.1,"unit":"%","sourceType":"official","date":"2026-02-17","source":"https://os-world.github.io/"},"osworld-2":{"score":9.3,"unit":"%","sourceType":"official","date":"2026-02-17","source":"https://osworld-v2.xlang.ai/"},"terminal-bench":{"score":53.43,"unit":"%","sourceType":"official","date":"2026-02-17","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"}}},{"id":"gemini-1-5-pro-sept-2024","name":"Gemini 1.5 Pro (Sept 2024)","provider":"Google","openWeights":false,"release":"2024-09-24","aliases":["gemini-1.5-pro-002","Gemini-1.5-Pro-002","Gemini 1.5 Pro (002)","Gemini 1.5 Pro 002"],"page":{"en":"https://aimap.page/en/benchmarks/model/gemini-1-5-pro-sept-2024/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gemini-1-5-pro-sept-2024/"},"best":{"lmarena-text":{"score":1351.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1179.4,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":57.23,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":86.9,"unit":"%","sourceType":"official","date":"2024-09-24","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"mmlu-pro":{"score":70.25,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"humaneval":{"score":79.3,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"},"aime":{"score":23.06,"unit":"%","sourceType":"independent","date":"2025-02-25","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":70.39,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"hle":{"score":4.6,"unit":"%","sourceType":"compiled","date":"2024-09-24","source":"https://epoch.ai/benchmarks"}}},{"id":"gpt-4-turbo-nov-2023","name":"GPT-4 Turbo (Nov 2023)","provider":"OpenAI","openWeights":false,"release":"2023-11-06","aliases":["gpt-4-turbo-2024-04-09","gpt-4-0125-preview","gpt-4-1106-preview","GPT-4 Turbo Preview (January 2024)","GPT-4 Turbo Preview (Nov 2023)","gpt-4-turbo","GPT-4 Turbo (1106 preview)","GPT-4 (1106)","SWE-agent + GPT 4 (1106)","RAG + GPT 4 (1106)","GPT-4-Turbo-2024-04-09","GPT-4-Turbo (Nov 2023)","GPT-4-Turbo"],"page":{"en":"https://aimap.page/en/benchmarks/model/gpt-4-turbo-nov-2023/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gpt-4-turbo-nov-2023/"},"best":{"lmarena-text":{"score":1324.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1112,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"livecodebench":{"score":27.9,"unit":"%","sourceType":"official","date":"2025-04-07","source":"https://livecodebench.github.io/leaderboard.html"},"gpqa-diamond":{"score":42.36,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":79.6,"unit":"%","sourceType":"official","date":"2023-11-06","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"mmlu-pro":{"score":63.71,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"humaneval":{"score":81.7,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"},"swe-bench-verified":{"score":22.4,"unit":"%","sourceType":"official","date":"2024-04-02","source":"https://www.swebench.com/#verified"},"math-level-5":{"score":40.02,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"}}},{"id":"gpt-4o-may-2024","name":"GPT-4o (May 2024)","provider":"OpenAI","openWeights":false,"release":"2024-05-13","aliases":["gpt-4o-2024-05-13","gpt-4o-2024-08-06","GPT-4o (2024-05-13)","GPT-4o","Agentless-1.5 + GPT 4o (2024-05-13)","AutoCodeRover (v20240620) + GPT 4o (2024-05-13)","MASAI + GPT 4o (2024-06-12)","EPAM AI/Run Developer Agent + GPT4o","AppMap Navie + GPT 4o (2024-05-13)","SWE-agent + GPT 4o (2024-05-13)","gpt-4o-20241120","GPT 4o","GPT 4o (2024-11-20)","GPT-4O-2024-08-06","GPT-4o (2024-08-06)"],"page":{"en":"https://aimap.page/en/benchmarks/model/gpt-4o-may-2024/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gpt-4o-may-2024/"},"best":{"lmarena-text":{"score":1346.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1161.8,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"livecodebench":{"score":28.4,"unit":"%","sourceType":"official","date":"2025-04-07","source":"https://livecodebench.github.io/leaderboard.html"},"gpqa-diamond":{"score":48.9,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":84.2,"unit":"%","sourceType":"official","date":"2024-05-13","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"mmlu-pro":{"score":72.55,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"swe-bench-verified":{"score":38.8,"unit":"%","sourceType":"official","date":"2024-10-28","source":"https://www.swebench.com/#verified"},"aime":{"score":6.25,"unit":"%","sourceType":"independent","date":"2025-02-25","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":51.05,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"}}},{"id":"gpt-5-mini","name":"GPT-5 mini","provider":"OpenAI","openWeights":false,"release":"2025-08-07","aliases":["gpt-5-mini-high","gpt-5-mini-2025-08-07_minimal","GPT-5 mini (minimal)","gpt-5-mini-2025-08-07_high","GPT-5 mini (high)","gpt-5-mini-2025-08-07_medium","GPT-5 mini (medium)","gpt-5-mini-2025-08-07_unknown","GPT-5 mini (unknown thinking)","gpt-5-mini-2025-08-07","GPT-5-Mini","GPT 5 mini","GPT 5 mini (2025-08-07) (medium)","GPT-5-mini-2025-08-07 (FC)","GPT-5-mini-2025-08-07 (Prompt)"],"page":{"en":"https://aimap.page/en/benchmarks/model/gpt-5-mini/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gpt-5-mini/"},"best":{"lmarena-text":{"score":1389.9,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1183.2,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":75,"unit":"%","sourceType":"independent","date":"2025-10-30","source":"https://epoch.ai/benchmarks"},"swe-bench-verified":{"score":64.67,"unit":"%","sourceType":"independent","date":"2026-02-01","source":"https://epoch.ai/benchmarks"},"aime":{"score":86.67,"unit":"%","sourceType":"independent","date":"2025-10-30","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":97.85,"unit":"%","sourceType":"independent","date":"2025-10-30","source":"https://epoch.ai/benchmarks"},"hle":{"score":19.44,"unit":"%","sourceType":"compiled","date":"2025-08-07","source":"https://epoch.ai/benchmarks"},"terminal-bench":{"score":34.83,"unit":"%","sourceType":"official","date":"2025-08-07","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},"bfcl":{"score":55.46,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"gpt-5-1","name":"GPT-5.1","provider":"OpenAI","openWeights":false,"release":"2025-11-13","aliases":["gpt-5.1-high","gpt-5.1","gpt-5.1-medium","gpt-5.1-2025-11-13_none","GPT-5.1 (no thinking)","gpt-5.1-2025-11-13_medium","GPT-5.1 (medium)","gpt-5.1-2025-11-13_high","GPT-5.1 (high)","gpt-5.1-2025-11-13_low","GPT-5.1 (low)","gpt-5.1-2025-11-13_unknown","GPT-5.1 (unknown thinking)","gpt-5.1-thinking","gpt-5.1-instant"],"page":{"en":"https://aimap.page/en/benchmarks/model/gpt-5-1/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gpt-5-1/"},"best":{"lmarena-text":{"score":1455.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1395.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1251.4,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":87.63,"unit":"%","sourceType":"independent","date":"2025-11-13","source":"https://epoch.ai/benchmarks"},"mmlu-pro":{"score":86.4,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"swe-bench-verified":{"score":67.98,"unit":"%","sourceType":"independent","date":"2026-02-18","source":"https://epoch.ai/benchmarks"},"aime":{"score":88.61,"unit":"%","sourceType":"independent","date":"2025-11-13","source":"https://epoch.ai/benchmarks"},"hle":{"score":23.68,"unit":"%","sourceType":"compiled","date":"2025-11-13","source":"https://epoch.ai/benchmarks"},"terminal-bench":{"score":47.6,"unit":"%","sourceType":"official","date":"2025-11-16","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"}}},{"id":"kimi-k2-5","name":"Kimi K2.5","provider":"Moonshot AI","openWeights":true,"release":"2026-01-27","aliases":["kimi-k2.5-thinking","kimi-k2.5-instant","fireworks/kimi-k2p5","Kimi K2.5 (Fireworks)","kimi-k2.5","Kimi K2.5 (high)"],"page":{"en":"https://aimap.page/en/benchmarks/model/kimi-k2-5/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/kimi-k2-5/"},"best":{"lmarena-text":{"score":1450.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1436.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1252.2,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":87.6,"unit":"%","sourceType":"independent","date":"2026-02-02","source":"https://epoch.ai/benchmarks"},"swe-bench-verified":{"score":73.76,"unit":"%","sourceType":"independent","date":"2026-02-17","source":"https://epoch.ai/benchmarks"},"aime":{"score":92.2,"unit":"%","sourceType":"independent","date":"2026-02-02","source":"https://epoch.ai/benchmarks"},"hle":{"score":24.37,"unit":"%","sourceType":"compiled","date":"2026-01-27","source":"https://epoch.ai/benchmarks"},"osworld":{"score":63.3,"unit":"%","sourceType":"official","date":"2026-02-03","source":"https://os-world.github.io/"},"terminal-bench":{"score":43.2,"unit":"%","sourceType":"official","date":"2026-01-27","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"}}},{"id":"claude-3-opus","name":"Claude 3 Opus","provider":"Anthropic","openWeights":false,"release":"2024-02-29","aliases":["claude-3-opus-20240229","Claude 3 Opus (20240229)","SWE-agent + Claude 3 Opus","RAG + Claude 3 Opus","Claude-3-Opus"],"page":{"en":"https://aimap.page/en/benchmarks/model/claude-3-opus/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/claude-3-opus/"},"best":{"lmarena-text":{"score":1322.2,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1061.7,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":47.16,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":84.6,"unit":"%","sourceType":"official","date":"2024-02-29","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"mmlu-pro":{"score":68.45,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"swe-bench-verified":{"score":15.8,"unit":"%","sourceType":"official","date":"2024-04-02","source":"https://www.swebench.com/#verified"},"aime":{"score":4.72,"unit":"%","sourceType":"independent","date":"2025-02-25","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":37.48,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"}}},{"id":"claude-haiku-4-5","name":"Claude Haiku 4.5","provider":"Anthropic","openWeights":false,"release":"2025-10-15","aliases":["claude-haiku-4-5-20251001","claude-haiku-4-5-20251001_32K","claude-haiku-4-5-20251001_unknown","Claude Haiku 4.5 (unknown thinking)","Claude 4.5 Haiku","Claude 4.5 Haiku (high)","Claude-Haiku-4-5-20251001 (FC)","Claude-Haiku-4-5-20251001 (Prompt)"],"page":{"en":"https://aimap.page/en/benchmarks/model/claude-haiku-4-5/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/claude-haiku-4-5/"},"best":{"lmarena-text":{"score":1414,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1329.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"gpqa-diamond":{"score":71.21,"unit":"%","sourceType":"independent","date":"2025-10-22","source":"https://epoch.ai/benchmarks"},"swe-bench-verified":{"score":66.6,"unit":"%","sourceType":"official","date":"2026-02-17","source":"https://www.swebench.com/#verified"},"aime":{"score":66.67,"unit":"%","sourceType":"independent","date":"2025-10-22","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":96.36,"unit":"%","sourceType":"independent","date":"2025-10-22","source":"https://epoch.ai/benchmarks"},"terminal-bench":{"score":35.51,"unit":"%","sourceType":"official","date":"2025-10-15","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},"bfcl":{"score":68.7,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"claude-opus-4-1","name":"Claude Opus 4.1","provider":"Anthropic","openWeights":false,"release":"2025-08-05","aliases":["claude-opus-4-1-20250805-thinking-16k","claude-opus-4-1-20250805","claude-opus-4-1-20250805_27K","claude-opus-4-1-20250805_16K","claude-opus-4-1-20250805_unknown","Claude Opus 4.1 (unknown thinking)","claude-opus-4-1-20250805-thinking"],"page":{"en":"https://aimap.page/en/benchmarks/model/claude-opus-4-1/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/claude-opus-4-1/"},"best":{"lmarena-text":{"score":1449.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1389.9,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"gpqa-diamond":{"score":76.77,"unit":"%","sourceType":"independent","date":"2025-08-05","source":"https://epoch.ai/benchmarks"},"swe-bench-verified":{"score":73.35,"unit":"%","sourceType":"independent","date":"2026-02-11","source":"https://epoch.ai/benchmarks"},"aime":{"score":68.89,"unit":"%","sourceType":"independent","date":"2025-08-05","source":"https://epoch.ai/benchmarks"},"hle":{"score":11.52,"unit":"%","sourceType":"compiled","date":"2025-08-05","source":"https://epoch.ai/benchmarks"},"tau2-bench":{"score":82.4,"unit":"%","sourceType":"vendor","date":"2025-08-05","source":"https://www.anthropic.com/news/claude-opus-4-1"},"terminal-bench":{"score":38,"unit":"%","sourceType":"official","date":"2025-10-31","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"}}},{"id":"deepseek-v3-2","name":"DeepSeek-V3.2","provider":"DeepSeek","openWeights":true,"release":"2025-12-01","aliases":["deepseek-v3.2","deepseek-v3.2-thinking","deepseek-chat","deepseek-reasoner","DeepSeek-V3.2 (Thinking)","deepseek/deepseek-v3.2","DeepSeek-V3.2 (Thinking; Novita)","DeepSeek V3.2","DeepSeek V3.2 (high)","DeepSeek-V3.2-Thinking"],"page":{"en":"https://aimap.page/en/benchmarks/model/deepseek-v3-2/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/deepseek-v3-2/"},"best":{"lmarena-text":{"score":1424.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1362.2,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"gpqa-diamond":{"score":83.42,"unit":"%","sourceType":"independent","date":"2025-12-16","source":"https://epoch.ai/benchmarks"},"mmlu-pro":{"score":85,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"swe-bench-verified":{"score":70,"unit":"%","sourceType":"official","date":"2026-02-17","source":"https://www.swebench.com/#verified"},"aime":{"score":87.82,"unit":"%","sourceType":"independent","date":"2025-12-16","source":"https://epoch.ai/benchmarks"},"tau2-bench":{"score":81.1,"unit":"%","sourceType":"vendor","date":"2025-12-01","source":"https://huggingface.co/deepseek-ai/DeepSeek-V3.2/resolve/main/assets/paper.pdf"},"terminal-bench":{"score":39.55,"unit":"%","sourceType":"official","date":"2025-12-01","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"}}},{"id":"gemini-1-5-flash-sep-2024","name":"Gemini 1.5 Flash (Sep 2024)","provider":"Google","openWeights":false,"release":"2024-09-24","aliases":["gemini-1.5-flash-002","Gemini 1.5 Flash (002)","Gemini 1.5 Flash 002","Gemini-1.5-Flash-002"],"page":{"en":"https://aimap.page/en/benchmarks/model/gemini-1-5-flash-sep-2024/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gemini-1-5-flash-sep-2024/"},"best":{"lmarena-text":{"score":1309.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1141.4,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":47.32,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":73.9,"unit":"%","sourceType":"official","date":"2024-09-24","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"mmlu-pro":{"score":64.09,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"humaneval":{"score":75.6,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"},"aime":{"score":16.25,"unit":"%","sourceType":"independent","date":"2025-02-25","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":61.87,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"}}},{"id":"gemini-3-flash","name":"Gemini 3 Flash","provider":"Google","openWeights":false,"release":"2025-12-17","aliases":["gemini-3-flash","gemini-3-flash (thinking-minimal)","gemini-3-flash-preview_high","Gemini 3 Flash Preview","gemini-3-flash-preview","Gemini 3 Flash (high)"],"page":{"en":"https://aimap.page/en/benchmarks/model/gemini-3-flash/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gemini-3-flash/"},"best":{"lmarena-text":{"score":1472.9,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1439.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1272.9,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":89.39,"unit":"%","sourceType":"independent","date":"2026-08-06","source":"https://epoch.ai/benchmarks"},"swe-bench-verified":{"score":75.8,"unit":"%","sourceType":"official","date":"2026-02-17","source":"https://www.swebench.com/#verified"},"aime":{"score":95.56,"unit":"%","sourceType":"independent","date":"2026-08-06","source":"https://epoch.ai/benchmarks"},"tau2-bench":{"score":76.8,"unit":"%","sourceType":"official","date":"2026-03-02","source":"https://taubench.com/"},"terminal-bench":{"score":64.27,"unit":"%","sourceType":"official","date":"2025-12-17","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"}}},{"id":"glm-5","name":"GLM-5","provider":"Zhipu AI (Z.ai)","openWeights":true,"release":"2026-02-11","aliases":["glm-5","GLM 5","GLM 5 (high)"],"page":{"en":"https://aimap.page/en/benchmarks/model/glm-5/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/glm-5/"},"best":{"lmarena-text":{"score":1457.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1434.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"gpqa-diamond":{"score":87.82,"unit":"%","sourceType":"independent","date":"2026-02-12","source":"https://epoch.ai/benchmarks"},"mmlu-pro":{"score":86,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"swe-bench-verified":{"score":72.8,"unit":"%","sourceType":"official","date":"2026-02-17","source":"https://www.swebench.com/#verified"},"aime":{"score":80,"unit":"%","sourceType":"independent","date":"2026-02-12","source":"https://epoch.ai/benchmarks"},"tau2-bench":{"score":73.7,"unit":"%","sourceType":"official","date":"2026-02-27","source":"https://taubench.com/"},"terminal-bench":{"score":52.42,"unit":"%","sourceType":"official","date":"2026-02-11","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"}}},{"id":"gpt-4-1-mini","name":"GPT-4.1 mini","provider":"OpenAI","openWeights":false,"release":"2025-04-14","aliases":["gpt-4.1-mini-2025-04-14","gpt-4.1-mini-20250414","GPT 4.1 mini","GPT 4.1 mini (2025-04-14)","GPT-4.1-mini-2025-04-14 (FC)","GPT-4.1-mini-2025-04-14 (Prompt)","GPT-4.1-mini"],"page":{"en":"https://aimap.page/en/benchmarks/model/gpt-4-1-mini/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gpt-4-1-mini/"},"best":{"lmarena-text":{"score":1382.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1200.8,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":65.85,"unit":"%","sourceType":"independent","date":"2025-04-14","source":"https://epoch.ai/benchmarks"},"swe-bench-verified":{"score":23.94,"unit":"%","sourceType":"official","date":"2025-07-20","source":"https://www.swebench.com/#verified"},"aime":{"score":44.72,"unit":"%","sourceType":"independent","date":"2025-04-14","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":87.29,"unit":"%","sourceType":"independent","date":"2025-04-14","source":"https://epoch.ai/benchmarks"},"tau2-bench":{"score":61.4,"unit":"%","sourceType":"official","date":"2025-06-09","source":"https://taubench.com/"},"bfcl":{"score":50.45,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"gpt-4o-mini","name":"GPT-4o mini","provider":"OpenAI","openWeights":false,"release":"2024-07-18","aliases":["gpt-4o-mini-2024-07-18","GPT 4o-mini","GPT-4o mini (2024-07-18)","GPT-4O-mini-2024-07-18","GPT-4o-mini"],"page":{"en":"https://aimap.page/en/benchmarks/model/gpt-4o-mini/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gpt-4o-mini/"},"best":{"lmarena-text":{"score":1317.6,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1097.1,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"livecodebench":{"score":26.7,"unit":"%","sourceType":"official","date":"2025-04-07","source":"https://livecodebench.github.io/leaderboard.html"},"gpqa-diamond":{"score":37.72,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":76.7,"unit":"%","sourceType":"official","date":"2024-07-18","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"mmlu-pro":{"score":63.09,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"aime":{"score":6.94,"unit":"%","sourceType":"independent","date":"2025-07-30","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":52.63,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"}}},{"id":"gpt-5-nano","name":"GPT-5 nano","provider":"OpenAI","openWeights":false,"release":"2025-08-07","aliases":["gpt-5-nano-high","gpt-5-nano-2025-08-07_low","GPT-5 nano (low)","gpt-5-nano-2025-08-07_minimal","GPT-5 nano (minimal)","gpt-5-nano-2025-08-07_high","GPT-5 nano (high)","gpt-5-nano-2025-08-07_medium","GPT-5 nano (medium)","gpt-5-nano-2025-08-07_unknown","GPT-5 nano (unknown thinking)","GPT-5-Nano","gpt-5-nano-2025-08-07","GPT 5 nano","GPT 5 nano (2025-08-07) (medium)"],"page":{"en":"https://aimap.page/en/benchmarks/model/gpt-5-nano/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gpt-5-nano/"},"best":{"lmarena-text":{"score":1337.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1146.2,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":69.44,"unit":"%","sourceType":"independent","date":"2025-10-30","source":"https://epoch.ai/benchmarks"},"swe-bench-verified":{"score":34.8,"unit":"%","sourceType":"official","date":"2025-08-07","source":"https://www.swebench.com/#verified"},"aime":{"score":81.11,"unit":"%","sourceType":"independent","date":"2025-10-31","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":95.24,"unit":"%","sourceType":"independent","date":"2025-08-20","source":"https://epoch.ai/benchmarks"},"terminal-bench":{"score":21.8,"unit":"%","sourceType":"official","date":"2025-08-07","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},"bfcl":{"score":51.45,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"gpt-5-5","name":"GPT-5.5","provider":"OpenAI","openWeights":false,"release":"2026-04-23","aliases":["gpt-5.5-high","gpt-5.5","gpt-5.5_none","GPT-5.5 (no thinking)","gpt-5.5_low","GPT-5.5 (low)","gpt-5.5-pre-release_xhigh","GPT-5.5 (xhigh)","gpt-5.5_xhigh","gpt-5.5_unknown","GPT-5.5 (unknown thinking)"],"page":{"en":"https://aimap.page/en/benchmarks/model/gpt-5-5/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gpt-5-5/"},"best":{"lmarena-text":{"score":1481.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1286.5,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":94,"unit":"%","sourceType":"independent","date":"2026-04-24","source":"https://epoch.ai/benchmarks"},"swe-bench-verified":{"score":80.58,"unit":"%","sourceType":"independent","date":"2026-04-24","source":"https://epoch.ai/benchmarks"},"aime":{"score":100,"unit":"%","sourceType":"independent","date":"2026-04-24","source":"https://epoch.ai/benchmarks"},"osworld-2":{"score":13,"unit":"%","sourceType":"official","date":"2026-04-23","source":"https://osworld-v2.xlang.ai/"},"terminal-bench":{"score":84.72,"unit":"%","sourceType":"official","date":"2026-04-23","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"}}},{"id":"llama-3-1-8b","name":"Llama 3.1-8B","provider":"Meta","openWeights":true,"release":"2024-07-23","aliases":["llama-3.1-8b-instruct","Llama-3.1-8B-Instruct","Llama 3.1 Instruct Turbo (8B)","Llama-3.1-8B-Instruct (Prompt)","Llama-3.1-8B","meta-llama/Llama-3.1-8B-Instruct","meta-llama/Llama-3.1-8B"],"page":{"en":"https://aimap.page/en/benchmarks/model/llama-3-1-8b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/llama-3-1-8b/"},"best":{"lmarena-text":{"score":1211.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":23.76,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"gpqa-diamond":{"score":26.96,"unit":"%","sourceType":"independent","date":"2026-08-27","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":56.1,"unit":"%","sourceType":"official","date":"2024-07-23","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"mmlu-pro":{"score":36.6,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"aime":{"score":1.67,"unit":"%","sourceType":"independent","date":"2026-08-27","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":22.88,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"bfcl":{"score":25.83,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"llama-3-3-70b","name":"Llama 3.3 70B","provider":"Meta","openWeights":true,"release":"2024-12-06","aliases":["llama-3.3-70b-instruct","Llama-3.3-70B-Instruct","Llama 3.3 Instruct Turbo (70B)","Llama3.3 70b instruct","Llama-3.3-70B-Instruct (FC)","meta-llama/Llama-3.3-70B-Instruct"],"page":{"en":"https://aimap.page/en/benchmarks/model/llama-3-3-70b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/llama-3-3-70b/"},"best":{"lmarena-text":{"score":1318,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":44.85,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"gpqa-diamond":{"score":47.44,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":79.1,"unit":"%","sourceType":"official","date":"2024-12-06","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"mmlu-pro":{"score":65.92,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"aime":{"score":5.14,"unit":"%","sourceType":"independent","date":"2025-02-25","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":41.6,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"bfcl":{"score":31.9,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"phi-4","name":"Phi-4","provider":"Microsoft Research","openWeights":true,"release":"2024-12-12","aliases":["phi-4","Phi-4 14b","Phi-4 (Prompt)","Phi-4-reasoning","microsoft/phi-4"],"page":{"en":"https://aimap.page/en/benchmarks/model/phi-4/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/phi-4/"},"best":{"lmarena-text":{"score":1256.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":30.36,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"gpqa-diamond":{"score":56.06,"unit":"%","sourceType":"independent","date":"2025-01-31","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":84.8,"unit":"%","sourceType":"paper","date":"2024-12-12","source":"http://arxiv.org/abs/2412.08905"},"mmlu-pro":{"score":70.4,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"aime":{"score":13.75,"unit":"%","sourceType":"independent","date":"2025-02-25","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":64.94,"unit":"%","sourceType":"independent","date":"2025-01-31","source":"https://epoch.ai/benchmarks"},"bfcl":{"score":28.79,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"claude-3-sonnet","name":"Claude 3 Sonnet","provider":"Anthropic","openWeights":false,"release":"2024-02-29","aliases":["claude-3-sonnet-20240229","Claude 3 Sonnet (20240229)","Claude-3-Sonnet"],"page":{"en":"https://aimap.page/en/benchmarks/model/claude-3-sonnet/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/claude-3-sonnet/"},"best":{"lmarena-text":{"score":1281.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1016.4,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":40.59,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":75.9,"unit":"%","sourceType":"official","date":"2024-02-29","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"mmlu-pro":{"score":56.8,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"aime":{"score":2.5,"unit":"%","sourceType":"independent","date":"2025-02-25","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":18.17,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"}}},{"id":"claude-3-5-haiku","name":"Claude 3.5 Haiku","provider":"Anthropic","openWeights":false,"release":"2024-10-22","aliases":["claude-3-5-haiku-20241022","Claude 3.5 Haiku (Oct 2024)","Claude 3.5 Haiku (20241022)","Claude-3-5-Haiku-20241022"],"page":{"en":"https://aimap.page/en/benchmarks/model/claude-3-5-haiku/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/claude-3-5-haiku/"},"best":{"lmarena-text":{"score":1324.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1126.8,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":38.13,"unit":"%","sourceType":"independent","date":"2025-03-12","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":74.3,"unit":"%","sourceType":"official","date":"2024-10-22","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"mmlu-pro":{"score":62.12,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"aime":{"score":4.31,"unit":"%","sourceType":"independent","date":"2025-02-25","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":46.36,"unit":"%","sourceType":"independent","date":"2025-03-12","source":"https://epoch.ai/benchmarks"}}},{"id":"claude-fable-5","name":"Claude Fable 5","provider":"Anthropic","openWeights":false,"release":"2026-06-09","aliases":["claude-fable-5-high","claude-fable-5_max","Claude Fable 5 (max)","claude-fable-5_low","Claude Fable 5 (low)","claude-fable-5_high","Claude Fable 5 (high)","Claude Fable 5 (Max)","Claude Fable 5 (XHigh)"],"page":{"en":"https://aimap.page/en/benchmarks/model/claude-fable-5/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/claude-fable-5/"},"best":{"lmarena-text":{"score":1503.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1624.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1308.8,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":85.86,"unit":"%","sourceType":"independent","date":"2026-08-06","source":"https://epoch.ai/benchmarks"},"aime":{"score":100,"unit":"%","sourceType":"independent","date":"2026-08-06","source":"https://epoch.ai/benchmarks"},"arc-agi-1":{"score":98.5,"unit":"%","sourceType":"official","date":"2026-10-22","source":"https://arcprize.org/leaderboard"}}},{"id":"claude-opus-4-8","name":"Claude Opus 4.8","provider":"Anthropic","openWeights":false,"release":"2026-05-28","aliases":["claude-opus-4-8-high","claude-opus-4-8","claude-opus-4-8_none","claude-opus-4-8_low","claude-opus-4-8_max","Claude Opus 4.8 (max)"],"page":{"en":"https://aimap.page/en/benchmarks/model/claude-opus-4-8/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/claude-opus-4-8/"},"best":{"lmarena-text":{"score":1481.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1555.9,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1286.4,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":85.35,"unit":"%","sourceType":"independent","date":"2026-08-06","source":"https://epoch.ai/benchmarks"},"aime":{"score":84.44,"unit":"%","sourceType":"independent","date":"2026-08-06","source":"https://epoch.ai/benchmarks"},"osworld-2":{"score":20.6,"unit":"%","sourceType":"official","date":"2026-05-28","source":"https://osworld-v2.xlang.ai/"}}},{"id":"claude-opus-5","name":"Claude Opus 5","provider":"Anthropic","openWeights":false,"release":"2026-07-24","aliases":["claude-opus-5-high","claude-opus-5","claude-opus-5_low","Claude Opus 5 (low)","claude-opus-5_max","Claude Opus 5 (max)","claude-opus-5_xhigh","Claude Opus 5 (xhigh)","claude-opus-5_high","Claude Opus 5 (high)","claude-opus-5_medium","Claude Opus 5 (medium)"],"page":{"en":"https://aimap.page/en/benchmarks/model/claude-opus-5/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/claude-opus-5/"},"best":{"lmarena-text":{"score":1490.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1656.9,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1289,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":93.88,"unit":"%","sourceType":"independent","date":"2026-07-24","source":"https://epoch.ai/benchmarks"},"aime":{"score":98.89,"unit":"%","sourceType":"independent","date":"2026-07-24","source":"https://epoch.ai/benchmarks"},"osworld-2":{"score":31.43,"unit":"%","sourceType":"official","date":"2026-07-24","source":"https://osworld-v2.xlang.ai/"}}},{"id":"deepseek-v3","name":"DeepSeek-V3","provider":"DeepSeek","openWeights":true,"release":"2024-12-26","aliases":["deepseek-v3","DeepSeek v3","DeepSeek-V3 Base","deepseek-chat","Deepseek-V3"],"page":{"en":"https://aimap.page/en/benchmarks/model/deepseek-v3/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/deepseek-v3/"},"best":{"lmarena-text":{"score":1358.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"livecodebench":{"score":14.9,"unit":"%","sourceType":"official","date":"2025-04-07","source":"https://livecodebench.github.io/leaderboard.html"},"gpqa-diamond":{"score":56.53,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":87.2,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"mmlu-pro":{"score":75.87,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"aime":{"score":15.83,"unit":"%","sourceType":"independent","date":"2025-02-25","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":64.85,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"}}},{"id":"gemini-3-8-flash","name":"Gemini 3.8 Flash","provider":"Google","openWeights":false,"release":"2026-09-02","aliases":["gemini-3.8-flash-high","gemini-3.8-flash_high","Gemini 3.8 Flash (high)","gemini-3.8-flash_unknown","Gemini 3.8 Flash (unknown)","Gemini 3.8 Flash (High)"],"page":{"en":"https://aimap.page/en/benchmarks/model/gemini-3-8-flash/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gemini-3-8-flash/"},"best":{"lmarena-text":{"score":1496.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1583.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1290.3,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":95.39,"unit":"%","sourceType":"independent","date":"2026-09-02","source":"https://epoch.ai/benchmarks"},"aime":{"score":98.89,"unit":"%","sourceType":"independent","date":"2026-09-02","source":"https://epoch.ai/benchmarks"},"hle":{"score":44.52,"unit":"%","sourceType":"compiled","date":"2026-09-02","source":"https://epoch.ai/benchmarks"},"arc-agi-1":{"score":98.5,"unit":"%","sourceType":"official","date":"2026-10-22","source":"https://arcprize.org/leaderboard"}}},{"id":"gemma-2-27b","name":"Gemma 2 27B","provider":"Google","openWeights":true,"release":"2024-06-24","aliases":["gemma-2-27b-it","Gemma 2 Instruct (27B)","Gemma-2-27B-it","google/gemma-2-27b-it","google/gemma-2-27b"],"page":{"en":"https://aimap.page/en/benchmarks/model/gemma-2-27b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gemma-2-27b/"},"best":{"lmarena-text":{"score":1289.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":36.17,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"gpqa-diamond":{"score":36.49,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":75.7,"unit":"%","sourceType":"official","date":"2024-06-24","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"mmlu-pro":{"score":56.54,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"aime":{"score":1.39,"unit":"%","sourceType":"independent","date":"2025-03-07","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":27.89,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"}}},{"id":"gemma-2-9b","name":"Gemma 2 9B","provider":"Google","openWeights":true,"release":"2024-06-24","aliases":["gemma-2-9b-it","Gemma 2 Instruct (9B)","Gemma-2-9B","Gemma-2-9B-it","google/gemma-2-9b-it","google/gemma-2-9b"],"page":{"en":"https://aimap.page/en/benchmarks/model/gemma-2-9b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gemma-2-9b/"},"best":{"lmarena-text":{"score":1267,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":32.07,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"gpqa-diamond":{"score":27.46,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":72.1,"unit":"%","sourceType":"official","date":"2024-06-24","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"mmlu-pro":{"score":45.1,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"aime":{"score":0.56,"unit":"%","sourceType":"independent","date":"2025-03-07","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":21.01,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"}}},{"id":"gemma-3-27b","name":"Gemma 3 27B","provider":"Google","openWeights":true,"release":"2025-03-12","aliases":["gemma-3-27b-it","Gemma-3-27b-it (Prompt)","Gemma-3-27B-it"],"page":{"en":"https://aimap.page/en/benchmarks/model/gemma-3-27b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gemma-3-27b/"},"best":{"lmarena-text":{"score":1365.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1159.8,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":47.73,"unit":"%","sourceType":"independent","date":"2026-08-27","source":"https://epoch.ai/benchmarks"},"mmlu-pro":{"score":67.5,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"aime":{"score":22.5,"unit":"%","sourceType":"independent","date":"2026-08-27","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":74.04,"unit":"%","sourceType":"independent","date":"2025-03-13","source":"https://epoch.ai/benchmarks"},"bfcl":{"score":29.47,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"gpt-4-5","name":"GPT-4.5","provider":"OpenAI","openWeights":false,"release":"2025-02-27","aliases":["gpt-4.5-preview-2025-02-27","GPT-4.5 Preview (Feb 2025)","GPT 4.5 Preview"],"page":{"en":"https://aimap.page/en/benchmarks/model/gpt-4-5/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gpt-4-5/"},"best":{"lmarena-text":{"score":1444.6,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1225.1,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":68.69,"unit":"%","sourceType":"independent","date":"2025-02-28","source":"https://epoch.ai/benchmarks"},"mmlu-pro":{"score":86.1,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"aime":{"score":37.78,"unit":"%","sourceType":"independent","date":"2025-02-28","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":78.63,"unit":"%","sourceType":"independent","date":"2025-02-28","source":"https://epoch.ai/benchmarks"},"hle":{"score":5.44,"unit":"%","sourceType":"compiled","date":"2025-02-27","source":"https://epoch.ai/benchmarks"}}},{"id":"gpt-5-6-sol","name":"GPT-5.6 Sol","provider":"OpenAI","openWeights":false,"release":"2026-07-09","aliases":["gpt-5.6-sol-xhigh","gpt-5.6-sol_none","GPT-5.6 Sol (none)","gpt-5.6-sol_low","GPT-5.6 Sol (low)","gpt-5.6-sol_max","GPT-5.6 Sol (max)","GPT-5.6-sol","GPT-5.6 Sol (XHigh)","GPT-5.6 Sol (Max)"],"page":{"en":"https://aimap.page/en/benchmarks/model/gpt-5-6-sol/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gpt-5-6-sol/"},"best":{"lmarena-text":{"score":1485.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1284.7,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":93.5,"unit":"%","sourceType":"independent","date":"2026-07-09","source":"https://epoch.ai/benchmarks"},"aime":{"score":100,"unit":"%","sourceType":"independent","date":"2026-07-09","source":"https://epoch.ai/benchmarks"},"arc-agi-2":{"score":92.5,"unit":"%","sourceType":"official","date":"2026-10-22","source":"https://arcprize.org/leaderboard"},"osworld-2":{"score":27.34,"unit":"%","sourceType":"official","date":"2026-07-09","source":"https://osworld-v2.xlang.ai/"}}},{"id":"grok-4","name":"Grok 4","provider":"xAI","openWeights":false,"release":"2025-07-09","aliases":["grok-4-0709","Grok-4-0709 (Prompt)","Grok-4-0709 (FC)","Grok-4"],"page":{"en":"https://aimap.page/en/benchmarks/model/grok-4/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/grok-4/"},"best":{"lmarena-text":{"score":1411,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1184.2,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":87,"unit":"%","sourceType":"independent","date":"2025-07-09","source":"https://epoch.ai/benchmarks"},"mmlu-pro":{"score":87,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"aime":{"score":84,"unit":"%","sourceType":"independent","date":"2025-07-09","source":"https://epoch.ai/benchmarks"},"terminal-bench":{"score":27.2,"unit":"%","sourceType":"official","date":"2025-11-02","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},"bfcl":{"score":62.97,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"kimi-k2","name":"Kimi K2 Thinking","provider":"Moonshot AI","openWeights":true,"release":"2025-07-11","aliases":["kimi-k2-thinking-turbo","Kimi K2 Thinking Turbo","kimi-k2-thinking","kimi-k2-0905-preview","Kimi K2","Lingxi v1.5 x Kimi K2","Kimi-K2-Thinking","Kimi-k2"],"page":{"en":"https://aimap.page/en/benchmarks/model/kimi-k2/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/kimi-k2/"},"best":{"lmarena-text":{"score":1430.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1322.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"gpqa-diamond":{"score":84.22,"unit":"%","sourceType":"independent","date":"2025-11-11","source":"https://epoch.ai/benchmarks"},"swe-bench-verified":{"score":71.2,"unit":"%","sourceType":"official","date":"2025-10-14","source":"https://www.swebench.com/#verified"},"aime":{"score":83.06,"unit":"%","sourceType":"independent","date":"2025-11-13","source":"https://epoch.ai/benchmarks"},"tau2-bench":{"score":70.6,"unit":"%","sourceType":"vendor","date":"2025-07-28","source":"https://arxiv.org/abs/2507.20534"},"terminal-bench":{"score":35.73,"unit":"%","sourceType":"official","date":"2025-11-06","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"}}},{"id":"kimi-k2-6","name":"Kimi K2.6","provider":"Moonshot AI","openWeights":true,"release":"2026-04-20","aliases":["kimi-k2.6","Kimi 2.6 (enabled)"],"page":{"en":"https://aimap.page/en/benchmarks/model/kimi-k2-6/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/kimi-k2-6/"},"best":{"lmarena-text":{"score":1460.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1509.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1264.9,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":90.78,"unit":"%","sourceType":"independent","date":"2026-05-01","source":"https://epoch.ai/benchmarks"},"swe-bench-verified":{"score":76.65,"unit":"%","sourceType":"independent","date":"2026-05-08","source":"https://epoch.ai/benchmarks"},"aime":{"score":96.11,"unit":"%","sourceType":"independent","date":"2026-05-02","source":"https://epoch.ai/benchmarks"},"osworld-2":{"score":4.6,"unit":"%","sourceType":"official","date":"2026-04-20","source":"https://osworld-v2.xlang.ai/"}}},{"id":"llama-2-70b","name":"Llama 2-70B","provider":"Meta","openWeights":true,"release":"2023-07-18","aliases":["llama-2-70b-chat","Llama-2-70b-chat-hf","Llama-2-70b-hf ","Llama 2 (70B)","LLAMA 2 70B","LLaMA 2 70B","LLaMA 2 70B    ","Llama-2-70b-chat","LLaMA2-Chat 70B","Llama-2-70B","meta-llama/Llama-2-70b-hf","meta-llama/Llama-2-70b-chat-hf"],"page":{"en":"https://aimap.page/en/benchmarks/model/llama-2-70b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/llama-2-70b/"},"best":{"lmarena-text":{"score":1170.6,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":18.37,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"gpqa-diamond":{"score":26.33,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":69.5,"unit":"%","sourceType":"official","date":"2023-07-18","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"mmlu-pro":{"score":37.53,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"aime":{"score":0,"unit":"%","sourceType":"independent","date":"2025-02-25","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":3.29,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"}}},{"id":"llama-3-1-70b","name":"Llama 3.1-70B","provider":"Meta","openWeights":true,"release":"2024-07-23","aliases":["llama-3.1-70b-instruct","Llama-3.1-70B-Instruct","Llama 3.1 Instruct Turbo (70B)","Llama-3.1-70B","meta-llama/Llama-3.1-70B-Instruct","meta-llama/Llama-3.1-70B"],"page":{"en":"https://aimap.page/en/benchmarks/model/llama-3-1-70b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/llama-3-1-70b/"},"best":{"lmarena-text":{"score":1293.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":43.41,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"gpqa-diamond":{"score":44.19,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":80.1,"unit":"%","sourceType":"official","date":"2024-07-23","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"mmlu-pro":{"score":52.47,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"aime":{"score":3.61,"unit":"%","sourceType":"independent","date":"2025-02-25","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":36.68,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"}}},{"id":"llama-4-maverick","name":"Llama 4 Maverick","provider":"Meta","openWeights":true,"release":"2025-04-05","aliases":["llama-4-maverick-17b-128e-instruct","Llama-4-Maverick-17B-128E-Instruct-FP8","Llama 4 Maverick (FP8)","Llama-4-Maverick-17B-128E-Instruct","Llama-4-Maverick-17B-128E-Instruct-FP8 (FC)"],"page":{"en":"https://aimap.page/en/benchmarks/model/llama-4-maverick/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/llama-4-maverick/"},"best":{"lmarena-text":{"score":1327,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1145.2,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":66.98,"unit":"%","sourceType":"independent","date":"2025-04-08","source":"https://epoch.ai/benchmarks"},"aime":{"score":20.56,"unit":"%","sourceType":"independent","date":"2025-04-08","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":73.02,"unit":"%","sourceType":"independent","date":"2025-04-08","source":"https://epoch.ai/benchmarks"},"hle":{"score":5.68,"unit":"%","sourceType":"compiled","date":"2025-04-05","source":"https://epoch.ai/benchmarks"},"bfcl":{"score":37.29,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"mistral-large-2-nov-2024","name":"Mistral Large 2 (Nov 2024)","provider":"Mistral AI","openWeights":true,"release":"2024-11-15","aliases":["mistral-large-2411","mistral-large-2411 (FC)","mistral-large-2411 (Prompt)","Mistral-Large-Instruct-2411","mistralai/Mistral-Large-Instruct-2411"],"page":{"en":"https://aimap.page/en/benchmarks/model/mistral-large-2-nov-2024/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/mistral-large-2-nov-2024/"},"best":{"lmarena-text":{"score":1305.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":46.52,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"gpqa-diamond":{"score":51.33,"unit":"%","sourceType":"independent","date":"2025-02-25","source":"https://epoch.ai/benchmarks"},"mmlu-pro":{"score":67.94,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"aime":{"score":7.78,"unit":"%","sourceType":"independent","date":"2025-02-25","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":50.28,"unit":"%","sourceType":"independent","date":"2025-02-25","source":"https://epoch.ai/benchmarks"},"bfcl":{"score":38.37,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"mistral-medium-3","name":"Mistral Medium 3","provider":"Mistral AI","openWeights":false,"release":"2025-05-07","aliases":["mistral-medium-2505","Mistral-Medium-2505","Mistral-Medium-2505 (FC)"],"page":{"en":"https://aimap.page/en/benchmarks/model/mistral-medium-3/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/mistral-medium-3/"},"best":{"lmarena-text":{"score":1387.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1155.2,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":59.53,"unit":"%","sourceType":"independent","date":"2025-05-07","source":"https://epoch.ai/benchmarks"},"aime":{"score":32.22,"unit":"%","sourceType":"independent","date":"2025-05-07","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":81.63,"unit":"%","sourceType":"independent","date":"2025-05-07","source":"https://epoch.ai/benchmarks"},"hle":{"score":4.52,"unit":"%","sourceType":"compiled","date":"2025-05-07","source":"https://epoch.ai/benchmarks"},"bfcl":{"score":37.69,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"mixtral-8x22b","name":"Mixtral 8x22B","provider":"Mistral AI","openWeights":true,"release":"2024-04-17","aliases":["mixtral-8x22b-instruct-v0.1","open-mixtral-8x22b","Mixtral-8x22B-v0.1","Mixtral (8x22B)","Mixtral-8x22B-Instruct-v0.1","mistralai/Mixtral-8x22B-Instruct-v0.1","mistralai/Mixtral-8x22B-v0.1"],"page":{"en":"https://aimap.page/en/benchmarks/model/mixtral-8x22b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/mixtral-8x22b/"},"best":{"lmarena-text":{"score":1229.6,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":33.89,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"gpqa-diamond":{"score":34.06,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":77.8,"unit":"%","sourceType":"official","date":"2024-04-17","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"mmlu-pro":{"score":56.33,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"humaneval":{"score":72,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"},"math-level-5":{"score":24.24,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"}}},{"id":"mixtral-8x7b","name":"Mixtral 8x7B","provider":"Mistral AI","openWeights":true,"release":"2023-12-11","aliases":["mixtral-8x7b-instruct-v0.1","Mixtral-8x7B-Instruct-v0.1","open-mixtral-8x7b","Mixtral-8x7B-v0.1","Mixtral 8x7b           ","mistralai/Mixtral-8x7B-Instruct-v0.1","mistralai/Mixtral-8x7B-v0.1"],"page":{"en":"https://aimap.page/en/benchmarks/model/mixtral-8x7b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/mixtral-8x7b/"},"best":{"lmarena-text":{"score":1197.2,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":23.82,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"gpqa-diamond":{"score":30.59,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":70.6,"unit":"%","sourceType":"paper","date":"2023-12-11","source":"https://arxiv.org/pdf/2401.04088"},"mmlu-pro":{"score":43.27,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"humaneval":{"score":39.6,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"},"math-level-5":{"score":9.29,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"}}},{"id":"qwen2-72b","name":"Qwen2-72B","provider":"Alibaba (Qwen)","openWeights":true,"release":"2024-06-07","aliases":["qwen2-72b-instruct","Qwen2 Instruct (72B)","Qwen2-72B-32k","Qwen/Qwen2-72B-Instruct","Qwen/Qwen2-72B"],"page":{"en":"https://aimap.page/en/benchmarks/model/qwen2-72b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/qwen2-72b/"},"best":{"lmarena-text":{"score":1261.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":43.59,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"gpqa-diamond":{"score":40.78,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":82.4,"unit":"%","sourceType":"official","date":"2024-06-07","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"mmlu-pro":{"score":55.59,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"math-level-5":{"score":39.07,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"cmmlu":{"score":89.65,"unit":"%","sourceType":"official","date":"2024-12-06","source":"https://github.com/haonan-li/CMMLU#排行榜"}}},{"id":"qwen3-5-397b-a17b","name":"Qwen3.5 397B-A17B","provider":"Alibaba (Qwen)","openWeights":true,"release":"2026-02-13","aliases":["qwen3.5-397b-a17b","qwen3.5-397b-a17b_none","Qwen3.5-397B-A17B"],"page":{"en":"https://aimap.page/en/benchmarks/model/qwen3-5-397b-a17b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/qwen3-5-397b-a17b/"},"best":{"lmarena-text":{"score":1441.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1399.9,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1246.9,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":85.86,"unit":"%","sourceType":"independent","date":"2026-08-07","source":"https://epoch.ai/benchmarks"},"mmlu-pro":{"score":87.8,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"aime":{"score":88.89,"unit":"%","sourceType":"independent","date":"2026-08-07","source":"https://epoch.ai/benchmarks"},"tau2-bench":{"score":84.4,"unit":"%","sourceType":"official","date":"2026-02-27","source":"https://taubench.com/"}}},{"id":"claude-sonnet-5-5","name":"Claude Sonnet 5.5","provider":"Anthropic","openWeights":false,"release":"2026-09-28","aliases":["claude-sonnet-5.5-xhigh","claude-sonnet-5.5-high","claude-sonnet-5-5_max","Claude Sonnet 5.5 (max)","claude-sonnet-5-5_xhigh","Claude Sonnet 5.5 (xhigh)","Sonnet 5.5 (xhigh)"],"page":{"en":"https://aimap.page/en/benchmarks/model/claude-sonnet-5-5/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/claude-sonnet-5-5/"},"best":{"lmarena-text":{"score":1475.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1774.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1268.3,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":95.58,"unit":"%","sourceType":"independent","date":"2026-09-29","source":"https://epoch.ai/benchmarks"},"aime":{"score":100,"unit":"%","sourceType":"independent","date":"2026-09-29","source":"https://epoch.ai/benchmarks"},"hle":{"score":46.12,"unit":"%","sourceType":"compiled","date":"2026-09-28","source":"https://epoch.ai/benchmarks"}}},{"id":"deepseek-r1-may-2025","name":"DeepSeek-R1 (May 2025)","provider":"DeepSeek","openWeights":true,"release":"2025-05-28","aliases":["deepseek-r1-0528","DeepSeek-R1-0528","deepseek-reasoner"],"page":{"en":"https://aimap.page/en/benchmarks/model/deepseek-r1-may-2025/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/deepseek-r1-may-2025/"},"best":{"lmarena-text":{"score":1421.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"livecodebench":{"score":70.5,"unit":"%","sourceType":"official","date":"2025-04-07","source":"https://livecodebench.github.io/leaderboard.html"},"gpqa-diamond":{"score":76.33,"unit":"%","sourceType":"independent","date":"2025-05-29","source":"https://epoch.ai/benchmarks"},"mmlu-pro":{"score":83.4,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"aime":{"score":66.39,"unit":"%","sourceType":"independent","date":"2025-05-29","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":96.64,"unit":"%","sourceType":"independent","date":"2025-05-29","source":"https://epoch.ai/benchmarks"}}},{"id":"deepseek-v3-mar-2025","name":"DeepSeek-V3 (Mar 2025)","provider":"DeepSeek","openWeights":true,"release":"2025-03-24","aliases":["deepseek-v3-0324","DeepSeek-V3-0324","DeepSeek V3 0324","SWE-Exp","Deepseek-V3-0324"],"page":{"en":"https://aimap.page/en/benchmarks/model/deepseek-v3-mar-2025/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/deepseek-v3-mar-2025/"},"best":{"lmarena-text":{"score":1395.2,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"gpqa-diamond":{"score":67.61,"unit":"%","sourceType":"independent","date":"2025-04-01","source":"https://epoch.ai/benchmarks"},"mmlu-pro":{"score":81.3,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"swe-bench-verified":{"score":42,"unit":"%","sourceType":"official","date":"2025-08-06","source":"https://www.swebench.com/#verified"},"aime":{"score":37.78,"unit":"%","sourceType":"independent","date":"2025-04-01","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":75.55,"unit":"%","sourceType":"independent","date":"2025-04-01","source":"https://epoch.ai/benchmarks"}}},{"id":"gemini-1-5-flash-may-2024","name":"Gemini 1.5 Flash (May 2024)","provider":"Google","openWeights":false,"release":"2024-05-14","aliases":["gemini-1.5-flash-001","Gemini 1.5 Flash (001)","gemini-1.5-flash-0514","Gemini 1.5 Flash (0514 preview)"],"page":{"en":"https://aimap.page/en/benchmarks/model/gemini-1-5-flash-may-2024/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gemini-1-5-flash-may-2024/"},"best":{"lmarena-text":{"score":1286.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1059.5,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":40.37,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":77.9,"unit":"%","sourceType":"official","date":"2024-05-23","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"aime":{"score":3.89,"unit":"%","sourceType":"independent","date":"2025-02-25","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":25.12,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"}}},{"id":"gemini-1-5-pro-may-2024","name":"Gemini 1.5 Pro (May 2024)","provider":"Google","openWeights":false,"release":"2024-05-14","aliases":["gemini-1.5-pro-001"],"page":{"en":"https://aimap.page/en/benchmarks/model/gemini-1-5-pro-may-2024/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gemini-1-5-pro-may-2024/"},"best":{"lmarena-text":{"score":1324,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1119.7,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":45.86,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":85.9,"unit":"%","sourceType":"vendor","date":"2024-05-14","source":"https://storage.googleapis.com/deepmind-media/gemini/gemini_v1_5_report.pdf"},"aime":{"score":6.81,"unit":"%","sourceType":"independent","date":"2025-02-25","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":40.75,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"}}},{"id":"gemini-3-5-flash","name":"Gemini 3.5 Flash","provider":"Google","openWeights":false,"release":"2026-05-19","aliases":["gemini-3.5-flash-high","gemini-3.5-flash-medium","gemini-3.5-flash_low","gemini-3.5-flash_minimal","gemini-3.5-flash_high"],"page":{"en":"https://aimap.page/en/benchmarks/model/gemini-3-5-flash/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gemini-3-5-flash/"},"best":{"lmarena-text":{"score":1477.6,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1499.2,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1284.4,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":88.89,"unit":"%","sourceType":"independent","date":"2026-08-06","source":"https://epoch.ai/benchmarks"},"swe-bench-verified":{"score":79.34,"unit":"%","sourceType":"independent","date":"2026-06-01","source":"https://epoch.ai/benchmarks"},"aime":{"score":88.89,"unit":"%","sourceType":"independent","date":"2026-08-06","source":"https://epoch.ai/benchmarks"}}},{"id":"gpt-4-1-nano","name":"GPT-4.1 nano","provider":"OpenAI","openWeights":false,"release":"2025-04-14","aliases":["gpt-4.1-nano-2025-04-14","GPT-4.1-nano-2025-04-14 (FC)","GPT-4.1-nano-2025-04-14 (Prompt)"],"page":{"en":"https://aimap.page/en/benchmarks/model/gpt-4-1-nano/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gpt-4-1-nano/"},"best":{"lmarena-text":{"score":1322.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1088.7,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":48.93,"unit":"%","sourceType":"independent","date":"2025-04-14","source":"https://epoch.ai/benchmarks"},"aime":{"score":28.89,"unit":"%","sourceType":"independent","date":"2025-04-14","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":70,"unit":"%","sourceType":"independent","date":"2025-04-14","source":"https://epoch.ai/benchmarks"},"bfcl":{"score":33.05,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"gpt-4o-nov-2024","name":"GPT-4o (Nov 2024)","provider":"OpenAI","openWeights":false,"release":"2024-11-20","aliases":["gpt-4o-2024-11-20","GPT-4o (November 2024)","GPT-4o"],"page":{"en":"https://aimap.page/en/benchmarks/model/gpt-4o-nov-2024/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gpt-4o-nov-2024/"},"best":{"gpqa-diamond":{"score":47.89,"unit":"%","sourceType":"independent","date":"2025-02-05","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":88.1,"unit":"%","sourceType":"paper","date":"2024-11-20","source":"http://arxiv.org/abs/2412.08905"},"swe-bench-verified":{"score":30.99,"unit":"%","sourceType":"independent","date":"2026-02-11","source":"https://epoch.ai/benchmarks"},"aime":{"score":6.25,"unit":"%","sourceType":"independent","date":"2025-02-25","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":49.77,"unit":"%","sourceType":"independent","date":"2025-02-05","source":"https://epoch.ai/benchmarks"},"hle":{"score":2.72,"unit":"%","sourceType":"compiled","date":"2024-11-20","source":"https://epoch.ai/benchmarks"}}},{"id":"gpt-oss-120b","name":"gpt-oss-120b","provider":"OpenAI","openWeights":true,"release":"2025-08-05","aliases":["openai/gpt-oss-120b_high","gpt-oss-120b_unknown","gpt-oss-120b (unknown thinking)","GPT-OSS-120B","GPT-oss-120B(high)"],"page":{"en":"https://aimap.page/en/benchmarks/model/gpt-oss-120b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gpt-oss-120b/"},"best":{"lmarena-text":{"score":1351.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"gpqa-diamond":{"score":75.76,"unit":"%","sourceType":"independent","date":"2025-12-11","source":"https://epoch.ai/benchmarks"},"mmlu-pro":{"score":80.8,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"swe-bench-verified":{"score":26,"unit":"%","sourceType":"official","date":"2025-08-07","source":"https://www.swebench.com/#verified"},"aime":{"score":88.89,"unit":"%","sourceType":"independent","date":"2025-12-11","source":"https://epoch.ai/benchmarks"},"terminal-bench":{"score":18.7,"unit":"%","sourceType":"official","date":"2025-11-01","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"}}},{"id":"grok-4-1-fast","name":"Grok 4.1 fast","provider":"xAI","openWeights":false,"release":"2025-11-19","aliases":["grok-4-1-fast-reasoning","Grok-4-1-fast-reasoning (FC)","Grok-4-1-fast-non-reasoning (FC)","Grok-4.1-Fast(Reasoning)"],"page":{"en":"https://aimap.page/en/benchmarks/model/grok-4-1-fast/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/grok-4-1-fast/"},"best":{"lmarena-text":{"score":1430.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1241.9,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1196.3,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"mmlu-pro":{"score":84.2,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"bfcl":{"score":69.57,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"grok-4-5","name":"Grok 4.5","provider":"xAI","openWeights":false,"release":"2026-07-08","aliases":["grok-4.5","grok-4.5_high","Grok 4.5 (high)"],"page":{"en":"https://aimap.page/en/benchmarks/model/grok-4-5/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/grok-4-5/"},"best":{"lmarena-text":{"score":1465.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1552.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1279,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":93.43,"unit":"%","sourceType":"independent","date":"2026-07-08","source":"https://epoch.ai/benchmarks"},"aime":{"score":97.78,"unit":"%","sourceType":"independent","date":"2026-07-08","source":"https://epoch.ai/benchmarks"}}},{"id":"grok-3-mini","name":"Grok-3 mini","provider":"xAI","openWeights":false,"release":"2025-04-09","aliases":["grok-3-mini-high","grok-3-mini-beta","grok-3-mini-beta_high","grok-3-mini-beta_low","Grok-3-Mini (High)","Grok-3-mini"],"page":{"en":"https://aimap.page/en/benchmarks/model/grok-3-mini/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/grok-3-mini/"},"best":{"lmarena-text":{"score":1363.9,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"livecodebench":{"score":62.6,"unit":"%","sourceType":"official","date":"2025-04-07","source":"https://livecodebench.github.io/leaderboard.html"},"gpqa-diamond":{"score":75.51,"unit":"%","sourceType":"independent","date":"2025-05-26","source":"https://epoch.ai/benchmarks"},"mmlu-pro":{"score":83,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"aime":{"score":62.22,"unit":"%","sourceType":"independent","date":"2025-04-10","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":90.94,"unit":"%","sourceType":"independent","date":"2025-04-10","source":"https://epoch.ai/benchmarks"}}},{"id":"llama-3-70b","name":"Llama 3-70B","provider":"Meta","openWeights":true,"release":"2024-04-18","aliases":["Meta-Llama-3-70B-Instruct","Llama 3 (70B)","Llama-3-70B","meta-llama/Meta-Llama-3-70B-Instruct","meta-llama/Meta-Llama-3-70B"],"page":{"en":"https://aimap.page/en/benchmarks/model/llama-3-70b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/llama-3-70b/"},"best":{"open-llm-leaderboard":{"score":36.37,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"gpqa-diamond":{"score":40.56,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":79.3,"unit":"%","sourceType":"official","date":"2024-04-18","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"mmlu-pro":{"score":52.78,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"aime":{"score":4.31,"unit":"%","sourceType":"independent","date":"2025-02-25","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":22.55,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"}}},{"id":"llama-3-8b","name":"Llama 3-8B","provider":"Meta","openWeights":true,"release":"2024-04-18","aliases":["Meta-Llama-3-8B-Instruct","Llama 3 (8B)","Llama-3-In 8b          ","Llama-3-8B","meta-llama/Meta-Llama-3-8B-Instruct","meta-llama/Meta-Llama-3-8B"],"page":{"en":"https://aimap.page/en/benchmarks/model/llama-3-8b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/llama-3-8b/"},"best":{"open-llm-leaderboard":{"score":23.91,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"gpqa-diamond":{"score":26.07,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":68.8,"unit":"%","sourceType":"official","date":"2024-04-18","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"mmlu-pro":{"score":35.36,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"aime":{"score":1.94,"unit":"%","sourceType":"independent","date":"2026-08-30","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":6.13,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"}}},{"id":"llama-3-2-1b","name":"Llama 3.2 1B","provider":"Meta","openWeights":true,"release":"2024-09-24","aliases":["llama-3.2-1b-instruct","Llama-3.2-1B-Instruct","Llama-3.2-1B-Instruct (FC)","Llama-3.2-1B","meta-llama/Llama-3.2-1B-Instruct","meta-llama/Llama-3.2-1B"],"page":{"en":"https://aimap.page/en/benchmarks/model/llama-3-2-1b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/llama-3-2-1b/"},"best":{"lmarena-text":{"score":1111.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":14.44,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"gpqa-diamond":{"score":23.93,"unit":"%","sourceType":"independent","date":"2026-08-30","source":"https://epoch.ai/benchmarks"},"mmlu-pro":{"score":11.95,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"aime":{"score":0.56,"unit":"%","sourceType":"independent","date":"2026-08-30","source":"https://epoch.ai/benchmarks"},"bfcl":{"score":10.82,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"llama-4-scout","name":"Llama 4 Scout","provider":"Meta","openWeights":true,"release":"2025-04-05","aliases":["llama-4-scout-17b-16e-instruct","Llama-4-Scout-17B-16E-Instruct","Llama-4-Scout-17B-16E-Instruct (FC)"],"page":{"en":"https://aimap.page/en/benchmarks/model/llama-4-scout/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/llama-4-scout/"},"best":{"lmarena-text":{"score":1321.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1127.4,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":51.83,"unit":"%","sourceType":"independent","date":"2025-04-08","source":"https://epoch.ai/benchmarks"},"aime":{"score":7.78,"unit":"%","sourceType":"independent","date":"2025-04-08","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":62.27,"unit":"%","sourceType":"independent","date":"2025-04-08","source":"https://epoch.ai/benchmarks"},"bfcl":{"score":28.13,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"minimax-m3","name":"MiniMax-M3","provider":"MiniMax","openWeights":true,"release":"2026-06-01","aliases":["minimax-m3","MiniMax-M3_none","MiniMax M3 (enabled)"],"page":{"en":"https://aimap.page/en/benchmarks/model/minimax-m3/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/minimax-m3/"},"best":{"lmarena-text":{"score":1440.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1481.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1236.6,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":81.31,"unit":"%","sourceType":"independent","date":"2026-08-10","source":"https://epoch.ai/benchmarks"},"aime":{"score":26.67,"unit":"%","sourceType":"independent","date":"2026-08-10","source":"https://epoch.ai/benchmarks"},"osworld-2":{"score":4.6,"unit":"%","sourceType":"official","date":"2026-06-01","source":"https://osworld-v2.xlang.ai/"}}},{"id":"ministral-8b","name":"Ministral 8B","provider":"Mistral AI","openWeights":true,"release":"2024-10-16","aliases":["ministral-8b-2410","Ministral-8B-Instruct-2410 (FC)","Ministral-8B-Instruct-2410","mistralai/Ministral-8B-Instruct-2410"],"page":{"en":"https://aimap.page/en/benchmarks/model/ministral-8b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/ministral-8b/"},"best":{"lmarena-text":{"score":1237.6,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":24.19,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"gpqa-diamond":{"score":27.15,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"mmlu-pro":{"score":37.93,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"math-level-5":{"score":14.94,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"bfcl":{"score":11.1,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"mistral-large-2-jul-2024","name":"Mistral Large 2 (Jul 2024)","provider":"Mistral AI","openWeights":true,"release":"2024-07-24","aliases":["mistral-large-2407","Mistral Large 2 (2407)","Mistral-Large-Instruct-2407"],"page":{"en":"https://aimap.page/en/benchmarks/model/mistral-large-2-jul-2024/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/mistral-large-2-jul-2024/"},"best":{"lmarena-text":{"score":1314.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"gpqa-diamond":{"score":49.02,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":80,"unit":"%","sourceType":"official","date":"2024-07-24","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"mmlu-pro":{"score":65.91,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"aime":{"score":8.47,"unit":"%","sourceType":"independent","date":"2025-02-25","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":44.82,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"}}},{"id":"o1","name":"o1","provider":"OpenAI","openWeights":false,"release":"2024-12-17","aliases":["o1-2024-12-17","o1-2024-12-17_low","o1 (low)","o1-2024-12-17_high","o1 (high)","o1-2024-12-17_medium","o1 (medium)","o1-2024-12-17_unknown","o1 (unknown thinking)","o1 (December 2024)"],"page":{"en":"https://aimap.page/en/benchmarks/model/o1/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/o1/"},"best":{"lmarena-text":{"score":1402.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1192.8,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":76.77,"unit":"%","sourceType":"independent","date":"2025-02-13","source":"https://epoch.ai/benchmarks"},"aime":{"score":73.33,"unit":"%","sourceType":"independent","date":"2026-07-15","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":94.71,"unit":"%","sourceType":"independent","date":"2025-02-13","source":"https://epoch.ai/benchmarks"},"hle":{"score":7.96,"unit":"%","sourceType":"compiled","date":"2024-12-17","source":"https://epoch.ai/benchmarks"}}},{"id":"o3-mini","name":"o3-mini","provider":"OpenAI","openWeights":false,"release":"2025-01-31","aliases":["o3-mini-high","o3-mini-2025-01-31_low","o3-mini-2025-01-31_high","o3-mini (high)","o3-mini-2025-01-31_medium","o3-mini (medium)","O3 Mini","Agentless Lite + O3 Mini (20250214)","O3-Mini-2025-01-31 (Low)","o3-mini-2025-01-31__low","O3-Mini-2025-01-31 (Med)","o3-mini-2025-01-31__medium","O3-Mini-2025-01-31 (High)","o3-mini-2025-01-31__high"],"page":{"en":"https://aimap.page/en/benchmarks/model/o3-mini/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/o3-mini/"},"best":{"lmarena-text":{"score":1363.6,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"livecodebench":{"score":51.1,"unit":"%","sourceType":"official","date":"2025-04-07","source":"https://livecodebench.github.io/leaderboard.html"},"gpqa-diamond":{"score":77.02,"unit":"%","sourceType":"independent","date":"2025-02-13","source":"https://epoch.ai/benchmarks"},"swe-bench-verified":{"score":42.4,"unit":"%","sourceType":"official","date":"2025-02-14","source":"https://www.swebench.com/#verified"},"aime":{"score":76.94,"unit":"%","sourceType":"independent","date":"2025-02-27","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":96.49,"unit":"%","sourceType":"independent","date":"2025-02-13","source":"https://epoch.ai/benchmarks"}}},{"id":"qwen-3-8-max","name":"Qwen 3.8 Max","provider":"Alibaba (Qwen)","openWeights":false,"release":"2026-07-19","aliases":["qwen3.8-max","qwen3.8-max_xhigh","Qwen3.8 Max (xhigh)"],"page":{"en":"https://aimap.page/en/benchmarks/model/qwen-3-8-max/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/qwen-3-8-max/"},"best":{"lmarena-text":{"score":1483.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1672.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1301.2,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":92.68,"unit":"%","sourceType":"independent","date":"2026-08-04","source":"https://epoch.ai/benchmarks"},"aime":{"score":99.44,"unit":"%","sourceType":"independent","date":"2026-08-04","source":"https://epoch.ai/benchmarks"}}},{"id":"qwen1-5-72b","name":"Qwen1.5-72B","provider":"Alibaba (Qwen)","openWeights":true,"release":"2024-02-04","aliases":["qwen1.5-72b-chat","Qwen1.5 (72B)","Qwen1.5-72B-Chat"],"page":{"en":"https://aimap.page/en/benchmarks/model/qwen1-5-72b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/qwen1-5-72b/"},"best":{"lmarena-text":{"score":1233.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"gpqa-diamond":{"score":28.82,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":77.4,"unit":"%","sourceType":"official","date":"","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"mmlu-pro":{"score":52.64,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"humaneval":{"score":59.1,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"},"cmmlu":{"score":83.54,"unit":"%","sourceType":"official","date":"2024-12-06","source":"https://github.com/haonan-li/CMMLU#排行榜"}}},{"id":"qwen3-max","name":"Qwen3-Max","provider":"Alibaba (Qwen)","openWeights":false,"release":"2025-09-23","aliases":["qwen3-max-2025-09-23","Qwen3-Max-Instruct","Qwen3-Max-Thinking"],"page":{"en":"https://aimap.page/en/benchmarks/model/qwen3-max/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/qwen3-max/"},"best":{"lmarena-text":{"score":1423.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"gpqa-diamond":{"score":72.6,"unit":"%","sourceType":"independent","date":"2025-10-06","source":"https://epoch.ai/benchmarks"},"mmlu-pro":{"score":85.7,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"aime":{"score":73.33,"unit":"%","sourceType":"independent","date":"2025-10-06","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":97.13,"unit":"%","sourceType":"independent","date":"2025-10-09","source":"https://epoch.ai/benchmarks"},"tau2-bench":{"score":72.2,"unit":"%","sourceType":"official","date":"2024-09-23","source":"https://taubench.com/"}}},{"id":"yi-34b","name":"Yi-34B","provider":"01.AI","openWeights":true,"release":"2023-11-02","aliases":["yi-34b-chat","Yi-34B-Chat","Yi (34B)","Yi 34B","Yi-Chat 34B","01-ai/Yi-34B-Chat","01-ai/Yi-34B","01-ai/Yi-34B-200K"],"page":{"en":"https://aimap.page/en/benchmarks/model/yi-34b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/yi-34b/"},"best":{"lmarena-text":{"score":1183.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":24.23,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"gpqa-diamond":{"score":14.74,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":76.2,"unit":"%","sourceType":"official","date":"2023-11-02","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"mmlu-pro":{"score":43.03,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"math-level-5":{"score":5.15,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"}}},{"id":"amazon-nova-pro","name":"Amazon Nova Pro","provider":"Amazon","openWeights":false,"release":"2024-12-03","aliases":["amazon-nova-pro-v1.0","amazon.nova-pro-v1:0","Nova Pro","Amazon-Nova-Pro-v1:0 (FC)"],"page":{"en":"https://aimap.page/en/benchmarks/model/amazon-nova-pro/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/amazon-nova-pro/"},"best":{"lmarena-text":{"score":1290.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1018.7,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"mmlu":{"score":82,"unit":"%","sourceType":"official","date":"2024-12-03","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"hle":{"score":4.4,"unit":"%","sourceType":"compiled","date":"2024-12-03","source":"https://epoch.ai/benchmarks"},"bfcl":{"score":24.97,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"claude-2","name":"Claude 2","provider":"Anthropic","openWeights":false,"release":"2023-07-11","aliases":["claude-2.0","claude-2","RAG + Claude 2"],"page":{"en":"https://aimap.page/en/benchmarks/model/claude-2/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/claude-2/"},"best":{"gpqa-diamond":{"score":34.66,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":78.5,"unit":"%","sourceType":"vendor","date":"2023-07-11","source":"https://www-cdn.anthropic.com/5c49cc247484cecf107c699baf29250302e5da70/claude-2-model-card.pdf"},"swe-bench-verified":{"score":4.4,"unit":"%","sourceType":"official","date":"2023-10-10","source":"https://www.swebench.com/#verified"},"aime":{"score":2.5,"unit":"%","sourceType":"independent","date":"2025-03-07","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":11.73,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"}}},{"id":"claude-3-5-sonnet-october-2024","name":"Claude 3.5 Sonnet (October 2024)","provider":"Anthropic","openWeights":false,"release":"2024-10-22","aliases":["claude-3-5-sonnet-20241022","Claude 3.5 Sonnet (Oct 2024)","Claude 3.5 Sonnet (20241022)"],"page":{"en":"https://aimap.page/en/benchmarks/model/claude-3-5-sonnet-october-2024/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/claude-3-5-sonnet-october-2024/"},"best":{"gpqa-diamond":{"score":55.3,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":87.3,"unit":"%","sourceType":"official","date":"2024-10-22","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"aime":{"score":8.47,"unit":"%","sourceType":"independent","date":"2025-02-25","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":56.95,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"hle":{"score":4.08,"unit":"%","sourceType":"compiled","date":"2024-10-22","source":"https://epoch.ai/benchmarks"}}},{"id":"claude-opus-5-5","name":"Claude Opus 5.5","provider":"Anthropic","openWeights":false,"release":"2026-09-22","aliases":["claude-opus-5.5-high","claude-opus-5-5_max","Claude Opus 5.5 (max)","Claude Opus 5.5 (High)","Claude Opus 5.5 (XHigh)","Claude Opus 5.5 (Max)"],"page":{"en":"https://aimap.page/en/benchmarks/model/claude-opus-5-5/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/claude-opus-5-5/"},"best":{"lmarena-text":{"score":1507.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"gpqa-diamond":{"score":90.59,"unit":"%","sourceType":"independent","date":"2026-09-22","source":"https://epoch.ai/benchmarks"},"aime":{"score":100,"unit":"%","sourceType":"independent","date":"2026-09-22","source":"https://epoch.ai/benchmarks"},"arc-agi-1":{"score":98.5,"unit":"%","sourceType":"official","date":"2026-10-22","source":"https://arcprize.org/leaderboard"},"arc-agi-2":{"score":93.3,"unit":"%","sourceType":"official","date":"2026-10-22","source":"https://arcprize.org/leaderboard"}}},{"id":"claude-sonnet-5","name":"Claude Sonnet 5","provider":"Anthropic","openWeights":false,"release":"2026-06-30","aliases":["claude-sonnet-5-high","claude-sonnet-5_max","Claude Sonnet 5 (max)","claude-sonnet-5_xhigh","Claude Sonnet 5 (xhigh)"],"page":{"en":"https://aimap.page/en/benchmarks/model/claude-sonnet-5/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/claude-sonnet-5/"},"best":{"lmarena-text":{"score":1461,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1540.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1264.5,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":90.53,"unit":"%","sourceType":"independent","date":"2026-07-01","source":"https://epoch.ai/benchmarks"},"aime":{"score":94.72,"unit":"%","sourceType":"independent","date":"2026-07-01","source":"https://epoch.ai/benchmarks"}}},{"id":"dbrx","name":"DBRX","provider":"Databricks","openWeights":true,"release":"2024-03-27","aliases":["dbrx-instruct","DBRX Instruct","databricks/dbrx-instruct","databricks/dbrx-base"],"page":{"en":"https://aimap.page/en/benchmarks/model/dbrx/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/dbrx/"},"best":{"open-llm-leaderboard":{"score":25.2,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"gpqa-diamond":{"score":32.89,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":74.1,"unit":"%","sourceType":"official","date":"","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"humaneval":{"score":70.1,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"},"math-level-5":{"score":11.65,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"}}},{"id":"deepseek-llm-67b","name":"DeepSeek LLM 67B","provider":"DeepSeek","openWeights":true,"release":"2023-11-29","aliases":["deepseek-llm-67b-chat","deepseek-ai/deepseek-llm-67b-chat"],"page":{"en":"https://aimap.page/en/benchmarks/model/deepseek-llm-67b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/deepseek-llm-67b/"},"best":{"lmarena-text":{"score":1184.9,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":27.31,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"gpqa-diamond":{"score":24.62,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"aime":{"score":0.83,"unit":"%","sourceType":"independent","date":"2026-08-28","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":6.39,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"}}},{"id":"deepseek-r1","name":"DeepSeek-R1","provider":"DeepSeek","openWeights":true,"release":"2025-01-20","aliases":["deepseek-r1"],"page":{"en":"https://aimap.page/en/benchmarks/model/deepseek-r1/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/deepseek-r1/"},"best":{"lmarena-text":{"score":1398.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"gpqa-diamond":{"score":71.72,"unit":"%","sourceType":"independent","date":"2025-05-26","source":"https://epoch.ai/benchmarks"},"mmlu-pro":{"score":84,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"aime":{"score":53.33,"unit":"%","sourceType":"independent","date":"2025-02-26","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":93.05,"unit":"%","sourceType":"independent","date":"2025-01-31","source":"https://epoch.ai/benchmarks"}}},{"id":"deepseek-v4-pro","name":"DeepSeek-V4-Pro","provider":"DeepSeek","openWeights":true,"release":"2026-04-24","aliases":["deepseek-v4-pro-high-20260813","deepseek-v4-pro","deepseek-v4-pro_none","DeepSeek v4 Pro (unknown thinking)","deepseek-v4-pro_high","DeepSeek v4 Pro (high)","deepseek-v4-pro_max","DeepSeek v4 Pro (max)"],"page":{"en":"https://aimap.page/en/benchmarks/model/deepseek-v4-pro/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/deepseek-v4-pro/"},"best":{"lmarena-text":{"score":1464.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1582,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"gpqa-diamond":{"score":90.91,"unit":"%","sourceType":"independent","date":"2026-08-06","source":"https://epoch.ai/benchmarks"},"swe-bench-verified":{"score":77.64,"unit":"%","sourceType":"independent","date":"2026-06-18","source":"https://epoch.ai/benchmarks"},"aime":{"score":96.67,"unit":"%","sourceType":"independent","date":"2026-06-17","source":"https://epoch.ai/benchmarks"}}},{"id":"gemini-2-0-flash-feb-2025","name":"Gemini 2.0 Flash (Feb 2025)","provider":"Google","openWeights":false,"release":"2025-02-05","aliases":["gemini-2.0-flash-001"],"page":{"en":"https://aimap.page/en/benchmarks/model/gemini-2-0-flash-feb-2025/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gemini-2-0-flash-feb-2025/"},"best":{"lmarena-text":{"score":1359.9,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1171.9,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":64.14,"unit":"%","sourceType":"independent","date":"2025-02-06","source":"https://epoch.ai/benchmarks"},"aime":{"score":31.11,"unit":"%","sourceType":"independent","date":"2025-02-25","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":82.17,"unit":"%","sourceType":"independent","date":"2025-02-06","source":"https://epoch.ai/benchmarks"}}},{"id":"gemini-2-5-flash-jun-2025","name":"Gemini 2.5 Flash (Jun 2025)","provider":"Google","openWeights":false,"release":"2025-06-17","aliases":["gemini-2.5-flash","Gemini 2.5 Flash","Gemini 2.5 Flash (2025-04-17)","Gemini-2.5-Flash (FC)","Gemini-2.5-Flash (Prompt)"],"page":{"en":"https://aimap.page/en/benchmarks/model/gemini-2-5-flash-jun-2025/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gemini-2-5-flash-jun-2025/"},"best":{"lmarena-text":{"score":1409.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1215.1,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"swe-bench-verified":{"score":28.73,"unit":"%","sourceType":"official","date":"2025-07-26","source":"https://www.swebench.com/#verified"},"terminal-bench":{"score":17.08,"unit":"%","sourceType":"official","date":"2025-06-17","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},"bfcl":{"score":56.24,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"gemini-3-5-flash-lite","name":"Gemini 3.5 Flash-Lite","provider":"Google","openWeights":false,"release":"2026-07-21","aliases":["gemini-3.5-flash-lite","gemini-3.5-flash-lite_low","gemini-3.5-flash-lite_minimal","gemini-3.5-flash-lite_high"],"page":{"en":"https://aimap.page/en/benchmarks/model/gemini-3-5-flash-lite/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gemini-3-5-flash-lite/"},"best":{"lmarena-text":{"score":1455.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1439.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1264.4,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":75.76,"unit":"%","sourceType":"independent","date":"2026-08-06","source":"https://epoch.ai/benchmarks"},"aime":{"score":60,"unit":"%","sourceType":"independent","date":"2026-08-06","source":"https://epoch.ai/benchmarks"}}},{"id":"gemini-3-6-flash","name":"Gemini 3.6 Flash","provider":"Google","openWeights":false,"release":"2026-07-21","aliases":["gemini-3.6-flash-high","gemini-3.6-flash_minimal","gemini-3.6-flash_low","gemini-3.6-flash_high"],"page":{"en":"https://aimap.page/en/benchmarks/model/gemini-3-6-flash/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gemini-3-6-flash/"},"best":{"lmarena-text":{"score":1482.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1537.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1279.7,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":85.86,"unit":"%","sourceType":"independent","date":"2026-08-07","source":"https://epoch.ai/benchmarks"},"aime":{"score":80,"unit":"%","sourceType":"independent","date":"2026-08-07","source":"https://epoch.ai/benchmarks"}}},{"id":"gemini-3-7-flash","name":"Gemini 3.7 Flash","provider":"Google","openWeights":false,"release":"2026-08-13","aliases":["gemini-3.7-flash-high","gemini-3.7-flash_high","Gemini 3.7 Flash (high)"],"page":{"en":"https://aimap.page/en/benchmarks/model/gemini-3-7-flash/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gemini-3-7-flash/"},"best":{"lmarena-text":{"score":1486.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1591.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1296,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":94.82,"unit":"%","sourceType":"independent","date":"2026-08-14","source":"https://epoch.ai/benchmarks"},"aime":{"score":97.22,"unit":"%","sourceType":"independent","date":"2026-08-14","source":"https://epoch.ai/benchmarks"}}},{"id":"gemini-4-argon","name":"Gemini 4 Argon","provider":"Google","openWeights":false,"release":"2026-09-30","aliases":["gemini-4-argon_high","Gemini 4 Argon (high)","Gemini 4 Argon (High)","Gemini 4 Argon (Medium)"],"page":{"en":"https://aimap.page/en/benchmarks/model/gemini-4-argon/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gemini-4-argon/"},"best":{"lmarena-text":{"score":1525.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1677.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"gpqa-diamond":{"score":96.4,"unit":"%","sourceType":"independent","date":"2026-10-13","source":"https://epoch.ai/benchmarks"},"aime":{"score":100,"unit":"%","sourceType":"independent","date":"2026-10-13","source":"https://epoch.ai/benchmarks"},"arc-agi-1":{"score":98.5,"unit":"%","sourceType":"official","date":"2026-10-22","source":"https://arcprize.org/leaderboard"}}},{"id":"gemma-3-12b","name":"Gemma 3 12B","provider":"Google","openWeights":true,"release":"2025-03-12","aliases":["gemma-3-12b-it","Gemma-3-12b-it (Prompt)","Gemma-3-12B-it"],"page":{"en":"https://aimap.page/en/benchmarks/model/gemma-3-12b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gemma-3-12b/"},"best":{"lmarena-text":{"score":1341.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"gpqa-diamond":{"score":39.46,"unit":"%","sourceType":"independent","date":"2026-08-28","source":"https://epoch.ai/benchmarks"},"mmlu-pro":{"score":60.6,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"aime":{"score":16.67,"unit":"%","sourceType":"independent","date":"2026-08-28","source":"https://epoch.ai/benchmarks"},"bfcl":{"score":30.43,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"gemma-3-4b","name":"Gemma 3 4B","provider":"Google","openWeights":true,"release":"2025-03-12","aliases":["gemma-3-4b-it","Gemma-3-4b-it (Prompt)","Gemma-3-4B-it"],"page":{"en":"https://aimap.page/en/benchmarks/model/gemma-3-4b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gemma-3-4b/"},"best":{"lmarena-text":{"score":1303.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"gpqa-diamond":{"score":23.23,"unit":"%","sourceType":"independent","date":"2026-08-28","source":"https://epoch.ai/benchmarks"},"mmlu-pro":{"score":43.6,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"aime":{"score":7.5,"unit":"%","sourceType":"independent","date":"2026-08-28","source":"https://epoch.ai/benchmarks"},"bfcl":{"score":19.62,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"gemma-4-26b-a4b","name":"Gemma 4 26B A4B","provider":"Google","openWeights":true,"release":"2026-04-02","aliases":["gemma-4-26b-a4b","gemma-4-26b-a4b-it_minimal"],"page":{"en":"https://aimap.page/en/benchmarks/model/gemma-4-26b-a4b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gemma-4-26b-a4b/"},"best":{"lmarena-text":{"score":1437.6,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1359,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1241.9,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":73.23,"unit":"%","sourceType":"independent","date":"2026-08-06","source":"https://epoch.ai/benchmarks"},"aime":{"score":82.22,"unit":"%","sourceType":"independent","date":"2026-08-28","source":"https://epoch.ai/benchmarks"}}},{"id":"glm-4-6","name":"GLM-4.6","provider":"Zhipu AI (Z.ai)","openWeights":true,"release":"2025-09-30","aliases":["glm-4.6","GLM 4.6","https://huggingface.co/zai-org/GLM-4.6","GLM 4.6 (T=1)","GLM-4.6 (FC thinking)"],"page":{"en":"https://aimap.page/en/benchmarks/model/glm-4-6/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/glm-4-6/"},"best":{"lmarena-text":{"score":1424.2,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1340,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"swe-bench-verified":{"score":68.2,"unit":"%","sourceType":"official","date":"2025-09-30","source":"https://www.swebench.com/#verified"},"terminal-bench":{"score":24.53,"unit":"%","sourceType":"official","date":"2025-09-30","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},"bfcl":{"score":72.38,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"glm-4-7","name":"GLM-4.7","provider":"Zhipu AI (Z.ai)","openWeights":true,"release":"2025-12-22","aliases":["glm-4.7","GLM 4.7"],"page":{"en":"https://aimap.page/en/benchmarks/model/glm-4-7/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/glm-4-7/"},"best":{"lmarena-text":{"score":1441.2,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1435,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"gpqa-diamond":{"score":83.33,"unit":"%","sourceType":"independent","date":"2026-01-29","source":"https://epoch.ai/benchmarks"},"aime":{"score":83.33,"unit":"%","sourceType":"independent","date":"2026-01-29","source":"https://epoch.ai/benchmarks"},"terminal-bench":{"score":33.39,"unit":"%","sourceType":"official","date":"2025-12-22","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"}}},{"id":"glm-5-1","name":"GLM-5.1","provider":"Zhipu AI (Z.ai)","openWeights":true,"release":"2026-04-07","aliases":["glm-5.1"],"page":{"en":"https://aimap.page/en/benchmarks/model/glm-5-1/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/glm-5-1/"},"best":{"lmarena-text":{"score":1464.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1508.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"gpqa-diamond":{"score":89.9,"unit":"%","sourceType":"independent","date":"2026-08-10","source":"https://epoch.ai/benchmarks"},"swe-bench-verified":{"score":74.17,"unit":"%","sourceType":"independent","date":"2026-05-15","source":"https://epoch.ai/benchmarks"},"aime":{"score":93.33,"unit":"%","sourceType":"independent","date":"2026-08-10","source":"https://epoch.ai/benchmarks"}}},{"id":"glm-5-3-flash","name":"GLM-5.3-Flash","provider":"Zhipu AI (Z.ai)","openWeights":true,"release":"2026-08-20","aliases":["glm-5.3-flash","glm-5.3-flash_max","GLM-5.3-Flash (max)"],"page":{"en":"https://aimap.page/en/benchmarks/model/glm-5-3-flash/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/glm-5-3-flash/"},"best":{"lmarena-text":{"score":1474.6,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1609.2,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1278.4,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":90.15,"unit":"%","sourceType":"independent","date":"2026-08-26","source":"https://epoch.ai/benchmarks"},"aime":{"score":93.89,"unit":"%","sourceType":"independent","date":"2026-08-26","source":"https://epoch.ai/benchmarks"}}},{"id":"gpt-3-5-turbo-jan-2024","name":"GPT-3.5 Turbo (Jan 2024)","provider":"OpenAI","openWeights":false,"release":"2024-01-25","aliases":["gpt-3.5-turbo-0125","GPT-3.5 Turbo (0125)"],"page":{"en":"https://aimap.page/en/benchmarks/model/gpt-3-5-turbo-jan-2024/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gpt-3-5-turbo-jan-2024/"},"best":{"lmarena-text":{"score":1225.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"gpqa-diamond":{"score":27.18,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":67.3,"unit":"%","sourceType":"official","date":"2024-01-25","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"aime":{"score":2.22,"unit":"%","sourceType":"independent","date":"2026-08-07","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":11.63,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"}}},{"id":"gpt-3-5-turbo-nov-2023","name":"GPT-3.5 Turbo (Nov 2023)","provider":"OpenAI","openWeights":false,"release":"2023-11-06","aliases":["gpt-3.5-turbo-1106","GPT-3.5 version 1106   ","GPT-3.5-Turbo (Nov 2023)"],"page":{"en":"https://aimap.page/en/benchmarks/model/gpt-3-5-turbo-nov-2023/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gpt-3-5-turbo-nov-2023/"},"best":{"lmarena-text":{"score":1204.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"gpqa-diamond":{"score":28.03,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":71.4,"unit":"%","sourceType":"paper","date":"2023-11-06","source":"http://arxiv.org/abs/2404.14219"},"humaneval":{"score":70.7,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"},"math-level-5":{"score":15.89,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"}}},{"id":"gpt-4-jun-2023","name":"GPT-4 (Jun 2023)","provider":"OpenAI","openWeights":false,"release":"2023-06-13","aliases":["gpt-4-0613","GPT-4 (0613)"],"page":{"en":"https://aimap.page/en/benchmarks/model/gpt-4-jun-2023/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gpt-4-jun-2023/"},"best":{"lmarena-text":{"score":1276.2,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"gpqa-diamond":{"score":30.65,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":82.4,"unit":"%","sourceType":"official","date":"2023-06-13","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"aime":{"score":1.11,"unit":"%","sourceType":"independent","date":"2025-10-23","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":22.97,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"}}},{"id":"gpt-4o-aug-2024","name":"GPT-4o (Aug 2024)","provider":"OpenAI","openWeights":false,"release":"2024-08-06","aliases":["gpt-4o-2024-08-06","GPT-4o (2024-08-06)","GPT 4o (Aug 2024)"],"page":{"en":"https://aimap.page/en/benchmarks/model/gpt-4o-aug-2024/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gpt-4o-aug-2024/"},"best":{"gpqa-diamond":{"score":49.21,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":84.3,"unit":"%","sourceType":"official","date":"2024-08-06","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"humaneval":{"score":87.2,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"},"aime":{"score":6.39,"unit":"%","sourceType":"independent","date":"2025-02-25","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":53.28,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"}}},{"id":"gpt-5-4-mini","name":"GPT-5.4 Mini","provider":"OpenAI","openWeights":false,"release":"2026-03-17","aliases":["gpt-5.4-mini-high","gpt-5.4-mini-2026-03-17_xhigh","GPT-5.4 mini (xhigh)","gpt-5.4-mini-2026-03-17_none","GPT-5.4 mini (none)","gpt-5.4-mini-2026-03-17_high","GPT-5.4 mini (high)"],"page":{"en":"https://aimap.page/en/benchmarks/model/gpt-5-4-mini/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gpt-5-4-mini/"},"best":{"lmarena-text":{"score":1447.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1397.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1250.8,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":86.87,"unit":"%","sourceType":"independent","date":"2026-08-07","source":"https://epoch.ai/benchmarks"},"aime":{"score":88.89,"unit":"%","sourceType":"independent","date":"2026-08-07","source":"https://epoch.ai/benchmarks"}}},{"id":"gpt-6-astra","name":"GPT-6 Astra","provider":"OpenAI","openWeights":false,"release":"2026-09-02","aliases":["gpt-6-astra_max","GPT-6 Astra (max)","gpt-6-astra_unknown","GPT-6 Astra (unknown thinking)","GPT 6 Astra","GPT-6 Astra (XHigh)","GPT-6 Astra (High)","GPT-6 Astra (Max)","GPT-6 Astra (Medium)"],"page":{"en":"https://aimap.page/en/benchmarks/model/gpt-6-astra/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gpt-6-astra/"},"best":{"gpqa-diamond":{"score":95.77,"unit":"%","sourceType":"independent","date":"2026-08-30","source":"https://epoch.ai/benchmarks"},"aime":{"score":100,"unit":"%","sourceType":"independent","date":"2026-08-30","source":"https://epoch.ai/benchmarks"},"hle":{"score":54.8,"unit":"%","sourceType":"compiled","date":"2026-09-03","source":"https://epoch.ai/benchmarks"},"arc-agi-1":{"score":98.5,"unit":"%","sourceType":"official","date":"2026-10-22","source":"https://arcprize.org/leaderboard"},"arc-agi-2":{"score":95,"unit":"%","sourceType":"official","date":"2026-10-22","source":"https://arcprize.org/leaderboard"}}},{"id":"gpt-oss-20b","name":"gpt-oss-20b","provider":"OpenAI","openWeights":true,"release":"2025-08-05","aliases":["gpt-oss-20b_medium","gpt-oss-20b_low","gpt-oss-20b_high","gpt-oss-20b_unknown","GPT-OSS-20B","GPT-oss-20B(medium)","GPT-oss-20B(high)"],"page":{"en":"https://aimap.page/en/benchmarks/model/gpt-oss-20b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gpt-oss-20b/"},"best":{"lmarena-text":{"score":1317.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"gpqa-diamond":{"score":60.8,"unit":"%","sourceType":"independent","date":"2026-08-27","source":"https://epoch.ai/benchmarks"},"mmlu-pro":{"score":73.14,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"aime":{"score":50.83,"unit":"%","sourceType":"independent","date":"2026-08-27","source":"https://epoch.ai/benchmarks"},"terminal-bench":{"score":3.4,"unit":"%","sourceType":"official","date":"2025-11-03","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"}}},{"id":"grok-4-3-beta","name":"Grok 4.3 Beta","provider":"xAI","openWeights":false,"release":"2026-04-17","aliases":["grok-4.3","grok-4.3_high"],"page":{"en":"https://aimap.page/en/benchmarks/model/grok-4-3-beta/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/grok-4-3-beta/"},"best":{"lmarena-text":{"score":1441.6,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1357.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1242.9,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":88.83,"unit":"%","sourceType":"independent","date":"2026-06-17","source":"https://epoch.ai/benchmarks"},"aime":{"score":93.33,"unit":"%","sourceType":"independent","date":"2026-06-17","source":"https://epoch.ai/benchmarks"}}},{"id":"grok-4-6","name":"Grok 4.6","provider":"xAI","openWeights":false,"release":"2026-08-12","aliases":["grok-4.6-high","grok-4.6_xhigh","Grok 4.6 (xhigh)","grok-4.6_high","Grok 4.6 (high)"],"page":{"en":"https://aimap.page/en/benchmarks/model/grok-4-6/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/grok-4-6/"},"best":{"lmarena-text":{"score":1454.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1617.2,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1263.5,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":94,"unit":"%","sourceType":"independent","date":"2026-08-12","source":"https://epoch.ai/benchmarks"},"aime":{"score":99.17,"unit":"%","sourceType":"independent","date":"2026-08-14","source":"https://epoch.ai/benchmarks"}}},{"id":"inkling","name":"Inkling","provider":"Thinking Machines","openWeights":true,"release":"2026-07-15","aliases":["inkling","Inkling_xhigh","Inkling (xhigh)"],"page":{"en":"https://aimap.page/en/benchmarks/model/inkling/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/inkling/"},"best":{"lmarena-text":{"score":1441,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1413.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"gpqa-diamond":{"score":88.26,"unit":"%","sourceType":"independent","date":"2026-08-05","source":"https://epoch.ai/benchmarks"},"aime":{"score":88.89,"unit":"%","sourceType":"independent","date":"2026-08-05","source":"https://epoch.ai/benchmarks"}}},{"id":"inkling-small","name":"Inkling-Small","provider":"Thinking Machines","openWeights":true,"release":"2026-07-15","aliases":["Inkling Small","inkling-small_xhigh","Inkling Small (xhigh)"],"page":{"en":"https://aimap.page/en/benchmarks/model/inkling-small/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/inkling-small/"},"best":{"lmarena-text":{"score":1405.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1408.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1206.3,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":88.51,"unit":"%","sourceType":"independent","date":"2026-08-14","source":"https://epoch.ai/benchmarks"},"aime":{"score":90,"unit":"%","sourceType":"independent","date":"2026-08-14","source":"https://epoch.ai/benchmarks"}}},{"id":"llama-3-1-405b","name":"Llama 3.1-405B","provider":"Meta","openWeights":true,"release":"2024-07-23","aliases":["Llama-3.1-405B-Instruct","Llama 3.1 Instruct Turbo (405B)","Llama-3.1-405B","LLaMA-3.1 405B Base"],"page":{"en":"https://aimap.page/en/benchmarks/model/llama-3-1-405b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/llama-3-1-405b/"},"best":{"gpqa-diamond":{"score":50.92,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":84.5,"unit":"%","sourceType":"official","date":"2024-07-23","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"mmlu-pro":{"score":73.3,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"aime":{"score":9.72,"unit":"%","sourceType":"independent","date":"2025-02-25","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":49.77,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"}}},{"id":"minimax-m2","name":"MiniMax-M2","provider":"MiniMax","openWeights":true,"release":"2025-10-27","aliases":["minimax-m2","MiniMax M2"],"page":{"en":"https://aimap.page/en/benchmarks/model/minimax-m2/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/minimax-m2/"},"best":{"lmarena-text":{"score":1343.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1297.2,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"mmlu-pro":{"score":82,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"swe-bench-verified":{"score":61,"unit":"%","sourceType":"official","date":"2025-11-24","source":"https://www.swebench.com/#verified"},"terminal-bench":{"score":30.04,"unit":"%","sourceType":"official","date":"2025-10-27","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"}}},{"id":"minimax-m2-5","name":"MiniMax-M2.5","provider":"MiniMax","openWeights":true,"release":"2026-02-12","aliases":["minimax-m2.5","Minimax m2.5","MiniMax M2.5","MiniMax M2.5 (high)"],"page":{"en":"https://aimap.page/en/benchmarks/model/minimax-m2-5/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/minimax-m2-5/"},"best":{"lmarena-text":{"score":1390.9,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1386.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"mmlu-pro":{"score":80.1,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"swe-bench-verified":{"score":75.8,"unit":"%","sourceType":"official","date":"2026-02-17","source":"https://www.swebench.com/#verified"},"terminal-bench":{"score":42.7,"unit":"%","sourceType":"official","date":"2026-02-12","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"}}},{"id":"mistral-7b-v0-2","name":"Mistral 7B v0.2","provider":"Mistral AI","openWeights":true,"release":"2023-12-11","aliases":["mistral-7b-instruct-v0.2","Mistral-7B-Instruct-v0.2","Mistral 7B","Mistral-7B-v0.2","mistralai/Mistral-7B-Instruct-v0.2"],"page":{"en":"https://aimap.page/en/benchmarks/model/mistral-7b-v0-2/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/mistral-7b-v0-2/"},"best":{"lmarena-text":{"score":1149.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":18.51,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu":{"score":62.5,"unit":"%","sourceType":"paper","date":"2023-12-11","source":"https://arxiv.org/pdf/2403.08295"},"mmlu-pro":{"score":30.84,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"humaneval":{"score":36,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"mistral-7b-v0-3","name":"Mistral 7B v0.3","provider":"Mistral AI","openWeights":true,"release":"2023-09-27","aliases":["Mistral-7B-Instruct-v0.3","open-mistral-7b","Mistral Instruct v0.3 (7B)","mistralai/Mistral-7B-Instruct-v0.3","mistralai/Mistral-7B-v0.3"],"page":{"en":"https://aimap.page/en/benchmarks/model/mistral-7b-v0-3/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/mistral-7b-v0-3/"},"best":{"open-llm-leaderboard":{"score":19.23,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"gpqa-diamond":{"score":15.18,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":59.9,"unit":"%","sourceType":"official","date":"2024-05-27","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"aime":{"score":0.28,"unit":"%","sourceType":"independent","date":"2026-08-30","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":3.6,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"}}},{"id":"mistral-large","name":"Mistral Large","provider":"Mistral AI","openWeights":false,"release":"2024-02-26","aliases":["mistral-large-2402","Mistral Large (2402)"],"page":{"en":"https://aimap.page/en/benchmarks/model/mistral-large/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/mistral-large/"},"best":{"lmarena-text":{"score":1242.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"gpqa-diamond":{"score":38.76,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":68.8,"unit":"%","sourceType":"official","date":"2024-02-26","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"aime":{"score":1.94,"unit":"%","sourceType":"independent","date":"2025-02-25","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":24.46,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"}}},{"id":"mistral-nemo","name":"Mistral NeMo","provider":"Mistral AI","openWeights":true,"release":"2024-07-18","aliases":["open-mistral-nemo-2407","Open-Mistral-Nemo-2407 (FC)","Open-Mistral-Nemo-2407 (Prompt)","Mistral-Nemo-Instruct-2407","Mistral-Nemo-Base-2407","mistralai/Mistral-Nemo-Instruct-2407","mistralai/Mistral-Nemo-Base-2407"],"page":{"en":"https://aimap.page/en/benchmarks/model/mistral-nemo/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/mistral-nemo/"},"best":{"open-llm-leaderboard":{"score":24.67,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"gpqa-diamond":{"score":29.89,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"mmlu-pro":{"score":44.81,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"math-level-5":{"score":10.83,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"bfcl":{"score":27.63,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"mistral-small-3-2","name":"Mistral Small 3.2","provider":"Mistral AI","openWeights":true,"release":"2025-06-20","aliases":["mistral-small-2506","mistral-small-3.2-2506","Mistral-small-2506 (FC)","Mistral-Small-2506 (Prompt)"],"page":{"en":"https://aimap.page/en/benchmarks/model/mistral-small-3-2/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/mistral-small-3-2/"},"best":{"lmarena-text":{"score":1356.2,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1139.8,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":49.05,"unit":"%","sourceType":"independent","date":"2026-08-28","source":"https://epoch.ai/benchmarks"},"aime":{"score":30.28,"unit":"%","sourceType":"independent","date":"2026-08-30","source":"https://epoch.ai/benchmarks"},"bfcl":{"score":37.15,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"muse-spark","name":"Muse Spark","provider":"Meta","openWeights":false,"release":"2026-04-08","aliases":["muse-spark"],"page":{"en":"https://aimap.page/en/benchmarks/model/muse-spark/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/muse-spark/"},"best":{"lmarena-text":{"score":1488.9,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1293.6,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":89.8,"unit":"%","sourceType":"independent","date":"2026-04-08","source":"https://epoch.ai/benchmarks"},"aime":{"score":88.9,"unit":"%","sourceType":"independent","date":"2026-04-08","source":"https://epoch.ai/benchmarks"},"hle":{"score":40.56,"unit":"%","sourceType":"compiled","date":"2026-04-08","source":"https://epoch.ai/benchmarks"}}},{"id":"o1-preview","name":"o1-preview","provider":"OpenAI","openWeights":false,"release":"2024-09-12","aliases":["o1-preview-2024-09-12","W&B Programmer O1 crosscheck5"],"page":{"en":"https://aimap.page/en/benchmarks/model/o1-preview/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/o1-preview/"},"best":{"lmarena-text":{"score":1388.6,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"gpqa-diamond":{"score":50.32,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"swe-bench-verified":{"score":64.6,"unit":"%","sourceType":"official","date":"2025-01-17","source":"https://www.swebench.com/#verified"},"aime":{"score":31.11,"unit":"%","sourceType":"independent","date":"2025-03-07","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":81.65,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"}}},{"id":"qwen-3-6-max-preview","name":"Qwen 3.6 Max (Preview)","provider":"Alibaba (Qwen)","openWeights":false,"release":"2026-04-20","aliases":["qwen3.6-max-preview"],"page":{"en":"https://aimap.page/en/benchmarks/model/qwen-3-6-max-preview/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/qwen-3-6-max-preview/"},"best":{"lmarena-text":{"score":1460.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1482.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"gpqa-diamond":{"score":87.37,"unit":"%","sourceType":"independent","date":"2026-08-07","source":"https://epoch.ai/benchmarks"},"swe-bench-verified":{"score":76.65,"unit":"%","sourceType":"independent","date":"2026-05-28","source":"https://epoch.ai/benchmarks"},"aime":{"score":91.11,"unit":"%","sourceType":"independent","date":"2026-08-07","source":"https://epoch.ai/benchmarks"}}},{"id":"qwen-3-6-plus","name":"Qwen 3.6 Plus","provider":"Alibaba (Qwen)","openWeights":false,"release":"2026-03-31","aliases":["qwen3.6-plus","Qwen 3.6 Plus (2026-04-02)"],"page":{"en":"https://aimap.page/en/benchmarks/model/qwen-3-6-plus/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/qwen-3-6-plus/"},"best":{"lmarena-text":{"score":1443.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1461.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"gpqa-diamond":{"score":88.38,"unit":"%","sourceType":"independent","date":"2026-08-07","source":"https://epoch.ai/benchmarks"},"swe-bench-verified":{"score":57.85,"unit":"%","sourceType":"independent","date":"2026-05-14","source":"https://epoch.ai/benchmarks"},"aime":{"score":93.33,"unit":"%","sourceType":"independent","date":"2026-08-07","source":"https://epoch.ai/benchmarks"}}},{"id":"qwen1-5-32b","name":"Qwen1.5-32B","provider":"Alibaba (Qwen)","openWeights":true,"release":"2024-02-04","aliases":["qwen1.5-32b-chat","qwen1.5-32B","Qwen1.5 (32B)","Qwen/Qwen1.5-32B-Chat","Qwen/Qwen1.5-32B"],"page":{"en":"https://aimap.page/en/benchmarks/model/qwen1-5-32b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/qwen1-5-32b/"},"best":{"lmarena-text":{"score":1204,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":29.26,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"gpqa-diamond":{"score":30.74,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":74.4,"unit":"%","sourceType":"official","date":"2024-02-04","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"}}},{"id":"qwen2-5-32b","name":"Qwen2.5-32B","provider":"Alibaba (Qwen)","openWeights":true,"release":"2024-09-17","aliases":["qwen2.5-32b-instruct","Qwen/Qwen2.5-32B-Instruct","Qwen/Qwen2.5-32B"],"page":{"en":"https://aimap.page/en/benchmarks/model/qwen2-5-32b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/qwen2-5-32b/"},"best":{"open-llm-leaderboard":{"score":46.6,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"gpqa-diamond":{"score":46.09,"unit":"%","sourceType":"independent","date":"2025-01-30","source":"https://epoch.ai/benchmarks"},"mmlu-pro":{"score":69.23,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"aime":{"score":7.36,"unit":"%","sourceType":"independent","date":"2025-02-25","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":56.07,"unit":"%","sourceType":"independent","date":"2025-01-30","source":"https://epoch.ai/benchmarks"}}},{"id":"qwen2-5-7b","name":"Qwen2.5-7B","provider":"Alibaba (Qwen)","openWeights":true,"release":"2024-09-19","aliases":["qwen2.5-7b-instruct","Qwen2.5 Instruct Turbo (7B)","Qwen/Qwen2.5-7B-Instruct","Qwen/Qwen2.5-7B"],"page":{"en":"https://aimap.page/en/benchmarks/model/qwen2-5-7b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/qwen2-5-7b/"},"best":{"open-llm-leaderboard":{"score":35.2,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"gpqa-diamond":{"score":35.48,"unit":"%","sourceType":"independent","date":"2026-08-30","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":72.9,"unit":"%","sourceType":"official","date":"2024-09-19","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"mmlu-pro":{"score":45,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"aime":{"score":2.5,"unit":"%","sourceType":"independent","date":"2026-08-30","source":"https://epoch.ai/benchmarks"}}},{"id":"qwen2-5-max","name":"Qwen2.5-Max","provider":"Alibaba (Qwen)","openWeights":false,"release":"2025-01-25","aliases":["qwen2.5-max","qwen-max-2025-01-25"],"page":{"en":"https://aimap.page/en/benchmarks/model/qwen2-5-max/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/qwen2-5-max/"},"best":{"lmarena-text":{"score":1373.9,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"gpqa-diamond":{"score":56.12,"unit":"%","sourceType":"independent","date":"2025-04-01","source":"https://epoch.ai/benchmarks"},"mmlu-pro":{"score":76.1,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"aime":{"score":16.11,"unit":"%","sourceType":"independent","date":"2025-04-01","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":67.18,"unit":"%","sourceType":"independent","date":"2025-04-01","source":"https://epoch.ai/benchmarks"}}},{"id":"qwen3-235b-a22b","name":"Qwen3-235B-A22B","provider":"Alibaba (Qwen)","openWeights":true,"release":"2025-04-28","aliases":["qwen3-235b-a22b","Qwen/Qwen3-235B-A22B"],"page":{"en":"https://aimap.page/en/benchmarks/model/qwen3-235b-a22b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/qwen3-235b-a22b/"},"best":{"lmarena-text":{"score":1375,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"livecodebench":{"score":59.3,"unit":"%","sourceType":"official","date":"2025-04-07","source":"https://livecodebench.github.io/leaderboard.html"},"gpqa-diamond":{"score":70.71,"unit":"%","sourceType":"independent","date":"2025-06-03","source":"https://epoch.ai/benchmarks"},"mmlu-pro":{"score":68.18,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"math-level-5":{"score":68.86,"unit":"%","sourceType":"independent","date":"2025-06-03","source":"https://epoch.ai/benchmarks"}}},{"id":"qwen3-5-35b-a3b","name":"Qwen3.5-35B-A3B","provider":"Alibaba (Qwen)","openWeights":true,"release":"2026-02-24","aliases":["qwen3.5-35b-a3b","qwen3.5-35b-a3b_none"],"page":{"en":"https://aimap.page/en/benchmarks/model/qwen3-5-35b-a3b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/qwen3-5-35b-a3b/"},"best":{"lmarena-text":{"score":1393.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1253.9,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"gpqa-diamond":{"score":81.19,"unit":"%","sourceType":"independent","date":"2026-08-28","source":"https://epoch.ai/benchmarks"},"mmlu-pro":{"score":85.3,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"aime":{"score":70,"unit":"%","sourceType":"independent","date":"2026-08-30","source":"https://epoch.ai/benchmarks"}}},{"id":"qwen3-7-plus","name":"Qwen3.7-Plus","provider":"Alibaba (Qwen)","openWeights":false,"release":"2026-06-02","aliases":["qwen3.7-plus","Qwen3.7 Plus","qwen3.7-plus_none","Qwen 3.7-Plus (thinking)"],"page":{"en":"https://aimap.page/en/benchmarks/model/qwen3-7-plus/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/qwen3-7-plus/"},"best":{"lmarena-text":{"score":1456,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1265.5,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":87.88,"unit":"%","sourceType":"independent","date":"2026-08-07","source":"https://epoch.ai/benchmarks"},"aime":{"score":93.33,"unit":"%","sourceType":"independent","date":"2026-08-07","source":"https://epoch.ai/benchmarks"},"osworld-2":{"score":2.8,"unit":"%","sourceType":"official","date":"2026-06-02","source":"https://osworld-v2.xlang.ai/"}}},{"id":"qwq-32b","name":"QwQ-32B","provider":"Alibaba (Qwen)","openWeights":true,"release":"2025-03-05","aliases":["qwq-32b","Qwen/QwQ-32B"],"page":{"en":"https://aimap.page/en/benchmarks/model/qwq-32b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/qwq-32b/"},"best":{"lmarena-text":{"score":1335.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":12.21,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"gpqa-diamond":{"score":65.34,"unit":"%","sourceType":"independent","date":"2026-08-28","source":"https://epoch.ai/benchmarks"},"mmlu-pro":{"score":69.07,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"aime":{"score":59.17,"unit":"%","sourceType":"independent","date":"2026-08-28","source":"https://epoch.ai/benchmarks"}}},{"id":"yi-1-5-34b","name":"Yi-1.5-34B","provider":"01.AI","openWeights":true,"release":"2024-05-13","aliases":["yi-1.5-34b-chat","Yi-1.5-34B-Chat","01-ai/Yi-1.5-34B-Chat","01-ai/Yi-1.5-34B-Chat-16K","01-ai/Yi-1.5-34B-32K","01-ai/Yi-1.5-34B"],"page":{"en":"https://aimap.page/en/benchmarks/model/yi-1-5-34b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/yi-1-5-34b/"},"best":{"lmarena-text":{"score":1212.9,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":33.36,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"gpqa-diamond":{"score":31.98,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"mmlu-pro":{"score":52.29,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"math-level-5":{"score":25.48,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"}}},{"id":"amazon-nova-lite","name":"Amazon Nova Lite","provider":"Amazon","openWeights":false,"release":"2024-12-03","aliases":["amazon-nova-lite-v1.0","amazon.nova-lite-v1:0","Nova Lite"],"page":{"en":"https://aimap.page/en/benchmarks/model/amazon-nova-lite/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/amazon-nova-lite/"},"best":{"lmarena-text":{"score":1260.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1018.8,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"mmlu":{"score":77,"unit":"%","sourceType":"official","date":"2024-12-03","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"hle":{"score":3.64,"unit":"%","sourceType":"compiled","date":"2024-12-03","source":"https://epoch.ai/benchmarks"}}},{"id":"claude-haiku-5-5","name":"Claude Haiku 5.5","provider":"Anthropic","openWeights":false,"release":"2026-10-07","aliases":["claude-haiku-5.5-high","claude-haiku-5-5_max","Claude Haiku 5.5 (max)","claude-haiku-5-5_xhigh","Claude Haiku 5.5 (xhigh)","claude-haiku-5-5_high","Claude Haiku 5.5 (high)","claude-haiku-5-5_unknown","Claude Haiku 5.5 (unknown)"],"page":{"en":"https://aimap.page/en/benchmarks/model/claude-haiku-5-5/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/claude-haiku-5-5/"},"best":{"lmarena-webdev":{"score":1586.9,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"gpqa-diamond":{"score":89.65,"unit":"%","sourceType":"independent","date":"2026-10-09","source":"https://epoch.ai/benchmarks"},"aime":{"score":98.89,"unit":"%","sourceType":"independent","date":"2026-10-07","source":"https://epoch.ai/benchmarks"},"hle":{"score":30.12,"unit":"%","sourceType":"compiled","date":"2026-10-07","source":"https://epoch.ai/benchmarks"}}},{"id":"command-r","name":"Command R+","provider":"Cohere","openWeights":true,"release":"2024-08-30","aliases":["command-r","c4ai-command-r-plus-08-2024","Command R Plus","Command-R+","CohereForAI/c4ai-command-r-plus-08-2024"],"page":{"en":"https://aimap.page/en/benchmarks/model/command-r/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/command-r/"},"best":{"lmarena-text":{"score":1226.9,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":33.65,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu":{"score":69.4,"unit":"%","sourceType":"official","date":"2024-08-30","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"humaneval":{"score":56.7,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"deepseek-r1-distill-llama-70b","name":"DeepSeek-R1-Distill-Llama-70B","provider":"DeepSeek","openWeights":true,"release":"2025-01-20","aliases":["deepseek-ai/DeepSeek-R1-Distill-Llama-70B"],"page":{"en":"https://aimap.page/en/benchmarks/model/deepseek-r1-distill-llama-70b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/deepseek-r1-distill-llama-70b/"},"best":{"open-llm-leaderboard":{"score":27.81,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"gpqa-diamond":{"score":55.74,"unit":"%","sourceType":"independent","date":"2025-03-10","source":"https://epoch.ai/benchmarks"},"aime":{"score":51.39,"unit":"%","sourceType":"independent","date":"2025-03-07","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":89.9,"unit":"%","sourceType":"independent","date":"2025-03-10","source":"https://epoch.ai/benchmarks"}}},{"id":"deepseek-r1-distill-qwen-14b","name":"DeepSeek-R1-Distill-Qwen-14B","provider":"DeepSeek","openWeights":true,"release":"2025-01-20","aliases":["deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"],"page":{"en":"https://aimap.page/en/benchmarks/model/deepseek-r1-distill-qwen-14b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/deepseek-r1-distill-qwen-14b/"},"best":{"open-llm-leaderboard":{"score":38.22,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"gpqa-diamond":{"score":44.7,"unit":"%","sourceType":"independent","date":"2025-03-10","source":"https://epoch.ai/benchmarks"},"aime":{"score":50.56,"unit":"%","sourceType":"independent","date":"2026-08-28","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":87.12,"unit":"%","sourceType":"independent","date":"2025-03-11","source":"https://epoch.ai/benchmarks"}}},{"id":"gemini-1-0-pro","name":"Gemini 1.0 Pro","provider":"Google","openWeights":false,"release":"2023-12-13","aliases":["gemini-1.0-pro-001","Gemini 1.0 Pro (001)"],"page":{"en":"https://aimap.page/en/benchmarks/model/gemini-1-0-pro/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gemini-1-0-pro/"},"best":{"gpqa-diamond":{"score":33.96,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":70,"unit":"%","sourceType":"official","date":"2023-12-13","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"aime":{"score":1.11,"unit":"%","sourceType":"independent","date":"2025-02-25","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":11.24,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"}}},{"id":"gemini-1-5-flash-8b","name":"Gemini 1.5 Flash 8B","provider":"Google","openWeights":false,"release":"2024-10-03","aliases":["gemini-1.5-flash-8b-001"],"page":{"en":"https://aimap.page/en/benchmarks/model/gemini-1-5-flash-8b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gemini-1-5-flash-8b/"},"best":{"lmarena-text":{"score":1258.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1071.3,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":32.95,"unit":"%","sourceType":"independent","date":"2025-03-12","source":"https://epoch.ai/benchmarks"},"aime":{"score":4.58,"unit":"%","sourceType":"independent","date":"2025-02-25","source":"https://epoch.ai/benchmarks"}}},{"id":"gemini-2-5-pro-mar-2025","name":"Gemini 2.5 Pro (Mar 2025)","provider":"Google","openWeights":false,"release":"2025-03-25","aliases":["gemini-2.5-pro-exp-03-25","Gemini 2.5 Pro Exp (Mar 2025)","gemini-2.5-pro-preview-03-25","Gemini 2.5 Pro Preview (Mar 2025)","Gemini 2.5 Pro Experimental (March 2025)","Gemini-2.5-Pro-Exp-03-25"],"page":{"en":"https://aimap.page/en/benchmarks/model/gemini-2-5-pro-mar-2025/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gemini-2-5-pro-mar-2025/"},"best":{"gpqa-diamond":{"score":83.84,"unit":"%","sourceType":"independent","date":"2025-03-31","source":"https://epoch.ai/benchmarks"},"mmlu-pro":{"score":84.52,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"math-level-5":{"score":95.56,"unit":"%","sourceType":"independent","date":"2025-05-07","source":"https://epoch.ai/benchmarks"},"hle":{"score":18.16,"unit":"%","sourceType":"compiled","date":"2025-03-25","source":"https://epoch.ai/benchmarks"}}},{"id":"gemini-2-5-pro-may-2025","name":"Gemini 2.5 Pro (May 2025)","provider":"Google","openWeights":false,"release":"2025-05-06","aliases":["gemini-2.5-pro-preview-05-06","Gemini 2.5 Pro Preview (Jun 2025)","Gemini 2.5 Pro Preview (May 06 2025)","Gemini-2.5-Pro-05-06"],"page":{"en":"https://aimap.page/en/benchmarks/model/gemini-2-5-pro-may-2025/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gemini-2-5-pro-may-2025/"},"best":{"livecodebench":{"score":68.1,"unit":"%","sourceType":"official","date":"2025-04-07","source":"https://livecodebench.github.io/leaderboard.html"},"gpqa-diamond":{"score":66.67,"unit":"%","sourceType":"independent","date":"2025-06-03","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":95.9,"unit":"%","sourceType":"independent","date":"2025-05-08","source":"https://epoch.ai/benchmarks"},"hle":{"score":17.8,"unit":"%","sourceType":"compiled","date":"2025-05-06","source":"https://epoch.ai/benchmarks"}}},{"id":"gemini-3-1-flash-lite-preview","name":"Gemini-3.1-Flash-Lite-Preview","provider":"Google","openWeights":false,"release":null,"aliases":["gemini-3.1-flash-lite-preview"],"page":{"en":"https://aimap.page/en/benchmarks/model/gemini-3-1-flash-lite-preview/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gemini-3-1-flash-lite-preview/"},"best":{"lmarena-text":{"score":1432.9,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1256.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1234.6,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"mmlu-pro":{"score":86.2,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"gemma-2b","name":"Gemma 2B","provider":"Google","openWeights":true,"release":"2024-02-21","aliases":["gemma-2b","Gemma-2B","google/gemma-2b"],"page":{"en":"https://aimap.page/en/benchmarks/model/gemma-2b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gemma-2b/"},"best":{"open-llm-leaderboard":{"score":7.32,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu":{"score":42.3,"unit":"%","sourceType":"paper","date":"2024-02-21","source":"https://arxiv.org/pdf/2403.08295"},"mmlu-pro":{"score":15.85,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"humaneval":{"score":20.7,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"gemma-3-1b","name":"Gemma 3 1B","provider":"Google","openWeights":true,"release":"2025-03-12","aliases":["gemma-3-1b-it","Gemma-3-1b-it (Prompt)","Gemma-3-1B-it"],"page":{"en":"https://aimap.page/en/benchmarks/model/gemma-3-1b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gemma-3-1b/"},"best":{"gpqa-diamond":{"score":19.95,"unit":"%","sourceType":"independent","date":"2026-08-28","source":"https://epoch.ai/benchmarks"},"mmlu-pro":{"score":14.7,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"aime":{"score":1.11,"unit":"%","sourceType":"independent","date":"2026-08-28","source":"https://epoch.ai/benchmarks"},"bfcl":{"score":7.17,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"gemma-7b","name":"Gemma 7B","provider":"Google","openWeights":true,"release":"2024-02-21","aliases":["gemma-7b","Gemma (7B)","Gemma 7b               ","Gemma-7B","google/gemma-7b"],"page":{"en":"https://aimap.page/en/benchmarks/model/gemma-7b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gemma-7b/"},"best":{"open-llm-leaderboard":{"score":15.44,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu":{"score":66.1,"unit":"%","sourceType":"official","date":"2024-02-21","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"mmlu-pro":{"score":33.73,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"humaneval":{"score":28.7,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"glm-4-5","name":"GLM-4.5","provider":"Zhipu AI (Z.ai)","openWeights":true,"release":"2025-08-03","aliases":["glm-4.5","glm-4p5","https://huggingface.co/zai-org/GLM-4.5","GLM 4.5","GLM 4.5 (2025-08-22)"],"page":{"en":"https://aimap.page/en/benchmarks/model/glm-4-5/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/glm-4-5/"},"best":{"lmarena-text":{"score":1411,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"mmlu-pro":{"score":84.6,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"swe-bench-verified":{"score":64.2,"unit":"%","sourceType":"official","date":"2025-07-28","source":"https://www.swebench.com/#verified"},"hle":{"score":8.32,"unit":"%","sourceType":"compiled","date":"2025-08-03","source":"https://epoch.ai/benchmarks"}}},{"id":"glm-5-2","name":"GLM-5.2","provider":"Zhipu AI (Z.ai)","openWeights":true,"release":"2026-06-16","aliases":["glm-5.2_none","glm-5.2_low","glm-5.2_max"],"page":{"en":"https://aimap.page/en/benchmarks/model/glm-5-2/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/glm-5-2/"},"best":{"gpqa-diamond":{"score":71.21,"unit":"%","sourceType":"independent","date":"2026-08-10","source":"https://epoch.ai/benchmarks"},"swe-bench-verified":{"score":78.7,"unit":"%","sourceType":"independent","date":"2026-06-25","source":"https://epoch.ai/benchmarks"},"aime":{"score":28.89,"unit":"%","sourceType":"independent","date":"2026-08-10","source":"https://epoch.ai/benchmarks"}}},{"id":"gpt-4-mar-2023","name":"GPT-4 (Mar 2023)","provider":"OpenAI","openWeights":false,"release":"2023-03-14","aliases":["gpt-4-0314","GPT-4 (initial release)"],"page":{"en":"https://aimap.page/en/benchmarks/model/gpt-4-mar-2023/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gpt-4-mar-2023/"},"best":{"lmarena-text":{"score":1287.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"gpqa-diamond":{"score":35.73,"unit":"%","sourceType":"independent","date":"2025-10-23","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":86.4,"unit":"%","sourceType":"paper","date":"2023-03-14","source":"https://arxiv.org/pdf/2303.08774"},"aime":{"score":0.56,"unit":"%","sourceType":"independent","date":"2025-10-22","source":"https://epoch.ai/benchmarks"}}},{"id":"gpt-4-turbo-apr-2024","name":"GPT-4 Turbo (Apr 2024)","provider":"OpenAI","openWeights":false,"release":"2024-04-09","aliases":["gpt-4-turbo-2024-04-09","GPT-4 Turbo (2024-04-09)"],"page":{"en":"https://aimap.page/en/benchmarks/model/gpt-4-turbo-apr-2024/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gpt-4-turbo-apr-2024/"},"best":{"gpqa-diamond":{"score":46.59,"unit":"%","sourceType":"independent","date":"2025-02-27","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":81.3,"unit":"%","sourceType":"official","date":"2024-04-09","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"aime":{"score":6.67,"unit":"%","sourceType":"independent","date":"2025-02-27","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":46.73,"unit":"%","sourceType":"independent","date":"2025-02-27","source":"https://epoch.ai/benchmarks"}}},{"id":"gpt-5-4-nano","name":"GPT-5.4 Nano","provider":"OpenAI","openWeights":false,"release":"2026-03-17","aliases":["gpt-5.4-nano-high","gpt-5.4-nano-2026-03-17_none","GPT-5.4 nano (no thinking)","gpt-5.4-nano-2026-03-17_low","GPT-5.4 nano (low)","gpt-5.4-nano-2026-03-17_high","GPT-5.4 nano (high)"],"page":{"en":"https://aimap.page/en/benchmarks/model/gpt-5-4-nano/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gpt-5-4-nano/"},"best":{"lmarena-text":{"score":1401.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1199.3,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":78.47,"unit":"%","sourceType":"independent","date":"2026-04-14","source":"https://epoch.ai/benchmarks"},"aime":{"score":87.78,"unit":"%","sourceType":"independent","date":"2026-04-14","source":"https://epoch.ai/benchmarks"}}},{"id":"gpt-5-5-instant","name":"GPT-5.5 Instant","provider":"OpenAI","openWeights":false,"release":"2026-05-05","aliases":["gpt-5.5-instant"],"page":{"en":"https://aimap.page/en/benchmarks/model/gpt-5-5-instant/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gpt-5-5-instant/"},"best":{"lmarena-text":{"score":1472.9,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1276,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":82.51,"unit":"%","sourceType":"independent","date":"2026-08-02","source":"https://epoch.ai/benchmarks"},"aime":{"score":68.06,"unit":"%","sourceType":"independent","date":"2026-08-02","source":"https://epoch.ai/benchmarks"}}},{"id":"gpt-5-6-luna","name":"GPT-5.6 Luna","provider":"OpenAI","openWeights":false,"release":"2026-07-09","aliases":["gpt-5.6-luna-xhigh","gpt-5.6-luna_none","GPT-5.6 Luna (none)","gpt-5.6-luna_low","GPT-5.6 Luna (low)","gpt-5.6-luna_max","GPT-5.6 Luna (max)"],"page":{"en":"https://aimap.page/en/benchmarks/model/gpt-5-6-luna/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gpt-5-6-luna/"},"best":{"lmarena-text":{"score":1452.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1259.8,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":91.6,"unit":"%","sourceType":"independent","date":"2026-07-09","source":"https://epoch.ai/benchmarks"},"aime":{"score":98.33,"unit":"%","sourceType":"independent","date":"2026-07-09","source":"https://epoch.ai/benchmarks"}}},{"id":"gpt-5-6-terra","name":"GPT-5.6 Terra","provider":"OpenAI","openWeights":false,"release":"2026-07-09","aliases":["gpt-5.6-terra-xhigh","gpt-5.6-terra_none","GPT-5.6 Terra (none)","gpt-5.6-terra_low","GPT-5.6 Terra (low)","gpt-5.6-terra_max","GPT-5.6 Terra (max)"],"page":{"en":"https://aimap.page/en/benchmarks/model/gpt-5-6-terra/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gpt-5-6-terra/"},"best":{"lmarena-text":{"score":1465.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1268.2,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"gpqa-diamond":{"score":93.31,"unit":"%","sourceType":"independent","date":"2026-07-09","source":"https://epoch.ai/benchmarks"},"aime":{"score":99.72,"unit":"%","sourceType":"independent","date":"2026-07-09","source":"https://epoch.ai/benchmarks"}}},{"id":"gpt-6-1-sol","name":"GPT-6.1 Sol","provider":"OpenAI","openWeights":false,"release":"2026-09-29","aliases":["gpt-6.1-sol_max","GPT-6.1 Sol (max)","GPT-6.1 Sol (XHigh)","GPT-6.1 Sol (High)","GPT-6.1 Sol (Max)"],"page":{"en":"https://aimap.page/en/benchmarks/model/gpt-6-1-sol/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/gpt-6-1-sol/"},"best":{"gpqa-diamond":{"score":95.39,"unit":"%","sourceType":"independent","date":"2026-09-29","source":"https://epoch.ai/benchmarks"},"aime":{"score":100,"unit":"%","sourceType":"independent","date":"2026-09-29","source":"https://epoch.ai/benchmarks"},"arc-agi-1":{"score":98.5,"unit":"%","sourceType":"official","date":"2026-10-22","source":"https://arcprize.org/leaderboard"},"arc-agi-2":{"score":94.2,"unit":"%","sourceType":"official","date":"2026-10-22","source":"https://arcprize.org/leaderboard"}}},{"id":"granite-3-1-8b-instruct","name":"Granite-3.1-8B-Instruct","provider":"IBM","openWeights":true,"release":null,"aliases":["granite-3.1-8b-instruct","Granite-3.1-8B-Instruct (FC)","ibm-granite/granite-3.1-8b-instruct"],"page":{"en":"https://aimap.page/en/benchmarks/model/granite-3-1-8b-instruct/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/granite-3-1-8b-instruct/"},"best":{"lmarena-text":{"score":1208.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":30.6,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu-pro":{"score":41.03,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"bfcl":{"score":27.1,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"grok-4-7","name":"Grok 4.7","provider":"xAI","openWeights":false,"release":"2026-09-21","aliases":["grok-4.7-xhigh","grok-4.7_xhigh","Grok 4.7 (xhigh)"],"page":{"en":"https://aimap.page/en/benchmarks/model/grok-4-7/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/grok-4-7/"},"best":{"lmarena-text":{"score":1442.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1639.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"gpqa-diamond":{"score":92.74,"unit":"%","sourceType":"independent","date":"2026-09-22","source":"https://epoch.ai/benchmarks"},"aime":{"score":98.06,"unit":"%","sourceType":"independent","date":"2026-09-22","source":"https://epoch.ai/benchmarks"}}},{"id":"kimi-k2-jul-2025","name":"Kimi K2 (Jul 2025)","provider":"Moonshot AI","openWeights":true,"release":"2025-07-12","aliases":["kimi-k2-0711-preview","Kimi-K2-Instruct","Kimi K2 Instruct","moonshot/kimi-k2-0711-preview","Kimi K2","OpenHands + Kimi K2","kimi-k2-instruct","CodeSweep - SWE-agent - Kimi K2 Instruct"],"page":{"en":"https://aimap.page/en/benchmarks/model/kimi-k2-jul-2025/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/kimi-k2-jul-2025/"},"best":{"lmarena-text":{"score":1417.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"mmlu-pro":{"score":81,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"swe-bench-verified":{"score":65.4,"unit":"%","sourceType":"official","date":"2025-07-16","source":"https://www.swebench.com/#verified"},"terminal-bench":{"score":27.8,"unit":"%","sourceType":"official","date":"2025-11-01","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"}}},{"id":"llama-3-2-90b","name":"Llama 3.2 90B","provider":"Meta","openWeights":true,"release":"2024-09-24","aliases":["Llama-3.2-90B-Vision-Instruct","Llama 3.2 Vision Instruct Turbo (90B)"],"page":{"en":"https://aimap.page/en/benchmarks/model/llama-3-2-90b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/llama-3-2-90b/"},"best":{"gpqa-diamond":{"score":41.04,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":80.3,"unit":"%","sourceType":"official","date":"2024-09-24","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"aime":{"score":2.64,"unit":"%","sourceType":"independent","date":"2025-02-25","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":39.44,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"}}},{"id":"llama-3-2-3b","name":"Llama-3.2-3B-Instruct","provider":"Meta","openWeights":true,"release":"2024-09-24","aliases":["llama-3.2-3b-instruct","Llama-3.2-3B-Instruct (FC)","Llama-3.2-3B","meta-llama/Llama-3.2-3B-Instruct","meta-llama/Llama-3.2-3B"],"page":{"en":"https://aimap.page/en/benchmarks/model/llama-3-2-3b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/llama-3-2-3b/"},"best":{"lmarena-text":{"score":1166.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":24.2,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu-pro":{"score":22.17,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"bfcl":{"score":21.95,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"mistral-large-4","name":"Mistral Large 4","provider":"Mistral AI","openWeights":false,"release":"2026-10-06","aliases":["mistral-large-4-0_high","Mistral Large 4 (high)"],"page":{"en":"https://aimap.page/en/benchmarks/model/mistral-large-4/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/mistral-large-4/"},"best":{"lmarena-text":{"score":1429.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1541.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"gpqa-diamond":{"score":88.07,"unit":"%","sourceType":"independent","date":"2026-10-12","source":"https://epoch.ai/benchmarks"},"aime":{"score":98.33,"unit":"%","sourceType":"independent","date":"2026-10-12","source":"https://epoch.ai/benchmarks"}}},{"id":"muse-spark-1-1","name":"Muse Spark 1.1","provider":"Meta","openWeights":false,"release":"2026-07-09","aliases":["muse-spark-1.1"],"page":{"en":"https://aimap.page/en/benchmarks/model/muse-spark-1-1/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/muse-spark-1-1/"},"best":{"lmarena-text":{"score":1490.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1542.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1281.1,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"o1-mini","name":"o1-mini","provider":"OpenAI","openWeights":false,"release":"2024-09-12","aliases":["o1-mini-2024-09-12_high","o1-mini (high)","o1-mini-2024-09-12_medium","o1-mini (medium)"],"page":{"en":"https://aimap.page/en/benchmarks/model/o1-mini/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/o1-mini/"},"best":{"lmarena-text":{"score":1336.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"gpqa-diamond":{"score":62.37,"unit":"%","sourceType":"independent","date":"2025-02-13","source":"https://epoch.ai/benchmarks"},"aime":{"score":46.94,"unit":"%","sourceType":"independent","date":"2025-03-06","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":89.18,"unit":"%","sourceType":"independent","date":"2025-02-13","source":"https://epoch.ai/benchmarks"}}},{"id":"phi-3-medium-14b","name":"phi-3-medium 14B","provider":"Microsoft","openWeights":true,"release":"2024-04-23","aliases":["Phi-3-medium-128k-instruct","Phi-3 (14B)","Phi-3 14b","Phi-3-medium","microsoft/Phi-3-medium-128k-instruct"],"page":{"en":"https://aimap.page/en/benchmarks/model/phi-3-medium-14b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/phi-3-medium-14b/"},"best":{"open-llm-leaderboard":{"score":32.03,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"gpqa-diamond":{"score":27.59,"unit":"%","sourceType":"independent","date":"2025-01-31","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":77.5,"unit":"%","sourceType":"official","date":"2024-04-23","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"math-level-5":{"score":17.56,"unit":"%","sourceType":"independent","date":"2025-01-31","source":"https://epoch.ai/benchmarks"}}},{"id":"phi-3-mini-3-8b","name":"phi-3-mini 3.8B","provider":"Microsoft","openWeights":true,"release":"2024-04-23","aliases":["phi-3-mini-128k-instruct","phi-3-mini-4k-instruct","Phi-3-mini-4k-instruct","Phi-3-mini","microsoft/Phi-3-mini-4k-instruct","microsoft/Phi-3-mini-128k-instruct"],"page":{"en":"https://aimap.page/en/benchmarks/model/phi-3-mini-3-8b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/phi-3-mini-3-8b/"},"best":{"lmarena-text":{"score":1129.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":27.56,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu":{"score":68.8,"unit":"%","sourceType":"paper","date":"2024-04-23","source":"http://arxiv.org/abs/2404.14219"},"humaneval":{"score":59.1,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"qwen-3-5-flash-hosted-35b-a3b","name":"Qwen 3.5 Flash (hosted 35B-A3B)","provider":"Alibaba (Qwen)","openWeights":false,"release":"2026-02-25","aliases":["qwen3.5-flash","Qwen3.5 Flash"],"page":{"en":"https://aimap.page/en/benchmarks/model/qwen-3-5-flash-hosted-35b-a3b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/qwen-3-5-flash-hosted-35b-a3b/"},"best":{"lmarena-text":{"score":1396,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1243.6,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"gpqa-diamond":{"score":82.32,"unit":"%","sourceType":"independent","date":"2026-08-07","source":"https://epoch.ai/benchmarks"},"aime":{"score":84.44,"unit":"%","sourceType":"independent","date":"2026-08-07","source":"https://epoch.ai/benchmarks"}}},{"id":"qwen1-5-110b","name":"Qwen1.5-110B","provider":"Alibaba (Qwen)","openWeights":true,"release":"2024-04-25","aliases":["qwen1.5-110b-chat","Qwen/Qwen1.5-110B-Chat","Qwen/Qwen1.5-110B"],"page":{"en":"https://aimap.page/en/benchmarks/model/qwen1-5-110b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/qwen1-5-110b/"},"best":{"lmarena-text":{"score":1234.2,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":33.13,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu-pro":{"score":49.93,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"cmmlu":{"score":88.32,"unit":"%","sourceType":"official","date":"2024-12-06","source":"https://github.com/haonan-li/CMMLU#排行榜"}}},{"id":"qwen1-5-14b","name":"Qwen1.5-14B","provider":"Alibaba (Qwen)","openWeights":true,"release":"2024-02-04","aliases":["qwen1.5-14b-chat","qwen1.5-14B","Qwen1.5 (14B)","Qwen1.5-14B-Chat","Qwen/Qwen1.5-14B-Chat","Qwen/Qwen1.5-14B"],"page":{"en":"https://aimap.page/en/benchmarks/model/qwen1-5-14b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/qwen1-5-14b/"},"best":{"lmarena-text":{"score":1191.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":23.57,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu":{"score":68.6,"unit":"%","sourceType":"official","date":"2024-02-04","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"mmlu-pro":{"score":38.02,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"qwen1-5-7b","name":"Qwen1.5-7B","provider":"Alibaba (Qwen)","openWeights":true,"release":"2024-02-04","aliases":["qwen1.5-7b-chat","Qwen1.5 (7B)","Qwen1.5-7B-Chat","Qwen/Qwen1.5-7B-Chat","Qwen/Qwen1.5-7B"],"page":{"en":"https://aimap.page/en/benchmarks/model/qwen1-5-7b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/qwen1-5-7b/"},"best":{"lmarena-text":{"score":1143.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":17.62,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu":{"score":62.6,"unit":"%","sourceType":"official","date":"2024-02-04","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"mmlu-pro":{"score":29.06,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"qwen2-5-coder-32b-instruct","name":"Qwen2.5-Coder-32B-Instruct","provider":"Alibaba (Qwen)","openWeights":true,"release":"2024-11-21","aliases":["qwen2.5-coder-32b-instruct","TTS(Bo8)","Skywork-SWE-32B + TTS(Bo8)","Qwen2.5 Coder 32B Instruct","Skywork-SWE-32B","Qwen2.5-Coder 32B Instruct","Qwen/Qwen2.5-Coder-32B-Instruct"],"page":{"en":"https://aimap.page/en/benchmarks/model/qwen2-5-coder-32b-instruct/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/qwen2-5-coder-32b-instruct/"},"best":{"lmarena-text":{"score":1270.6,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":39.89,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"humaneval":{"score":87.2,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"},"swe-bench-verified":{"score":47,"unit":"%","sourceType":"official","date":"2025-06-16","source":"https://www.swebench.com/#verified"}}},{"id":"qwen3-235b-a22b-thinking-jul-2025","name":"Qwen3-235B-A22B-Thinking (Jul 2025)","provider":"Alibaba (Qwen)","openWeights":true,"release":"2025-07-25","aliases":["qwen3-235b-a22b-thinking-2507","Qwen3-235B-A22B-Thinking-2507"],"page":{"en":"https://aimap.page/en/benchmarks/model/qwen3-235b-a22b-thinking-jul-2025/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/qwen3-235b-a22b-thinking-jul-2025/"},"best":{"lmarena-text":{"score":1400,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"gpqa-diamond":{"score":80.05,"unit":"%","sourceType":"independent","date":"2025-12-11","source":"https://epoch.ai/benchmarks"},"mmlu-pro":{"score":84.5,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"aime":{"score":86.67,"unit":"%","sourceType":"independent","date":"2025-12-10","source":"https://epoch.ai/benchmarks"}}},{"id":"qwen3-30b-a3b","name":"Qwen3-30B-A3B","provider":"Alibaba (Qwen)","openWeights":true,"release":"2025-04-28","aliases":["qwen3-30b-a3b","Qwen3-30B-A3B_none","Qwen3-30B-A3B-Thinking"],"page":{"en":"https://aimap.page/en/benchmarks/model/qwen3-30b-a3b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/qwen3-30b-a3b/"},"best":{"lmarena-text":{"score":1326.6,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"gpqa-diamond":{"score":50.38,"unit":"%","sourceType":"independent","date":"2026-08-30","source":"https://epoch.ai/benchmarks"},"mmlu-pro":{"score":78.5,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"aime":{"score":25.56,"unit":"%","sourceType":"independent","date":"2026-08-30","source":"https://epoch.ai/benchmarks"}}},{"id":"qwen3-30b-a3b-instruct-jul-2025","name":"Qwen3-30B-A3B-Instruct (Jul 2025)","provider":"Alibaba (Qwen)","openWeights":true,"release":"2025-07-29","aliases":["qwen3-30b-a3b-instruct-2507","Qwen3-30B-A3B-Instruct-2507 (FC)","Qwen3-30B-A3B-Instruct-2507 (Prompt)"],"page":{"en":"https://aimap.page/en/benchmarks/model/qwen3-30b-a3b-instruct-jul-2025/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/qwen3-30b-a3b-instruct-jul-2025/"},"best":{"lmarena-text":{"score":1382.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"gpqa-diamond":{"score":55.62,"unit":"%","sourceType":"independent","date":"2026-08-30","source":"https://epoch.ai/benchmarks"},"aime":{"score":62.22,"unit":"%","sourceType":"independent","date":"2026-08-30","source":"https://epoch.ai/benchmarks"},"bfcl":{"score":41.39,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"qwen3-32b","name":"Qwen3-32B","provider":"Alibaba (Qwen)","openWeights":true,"release":"2025-04-28","aliases":["qwen3-32b","Qwen3-32B_none","Qwen3-32B (FC)","Qwen3-32B (Prompt)"],"page":{"en":"https://aimap.page/en/benchmarks/model/qwen3-32b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/qwen3-32b/"},"best":{"lmarena-text":{"score":1346.9,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"gpqa-diamond":{"score":54.1,"unit":"%","sourceType":"independent","date":"2026-08-30","source":"https://epoch.ai/benchmarks"},"aime":{"score":23.06,"unit":"%","sourceType":"independent","date":"2026-08-30","source":"https://epoch.ai/benchmarks"},"bfcl":{"score":48.71,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"qwen3-coder-480b-a35b","name":"Qwen3-Coder-480B-A35B","provider":"Alibaba (Qwen)","openWeights":true,"release":"2025-07-31","aliases":["qwen3-coder-480b-a35b-instruct","Qwen3-Coder-480B-A35B-Instruct","Qwen 3 Coder 480B","https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct","OpenHands + Qwen3-Coder-480B-A35B-Instruct","Qwen3-Coder 480B/A35B Instruct"],"page":{"en":"https://aimap.page/en/benchmarks/model/qwen3-coder-480b-a35b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/qwen3-coder-480b-a35b/"},"best":{"lmarena-text":{"score":1387.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1274.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"swe-bench-verified":{"score":69.6,"unit":"%","sourceType":"official","date":"2025-08-05","source":"https://www.swebench.com/#verified"},"terminal-bench":{"score":27.19,"unit":"%","sourceType":"official","date":"2025-07-22","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"}}},{"id":"qwen3-5-122b-a10b","name":"Qwen3.5-122B-A10B","provider":"Alibaba (Qwen)","openWeights":true,"release":null,"aliases":["qwen3.5-122b-a10b"],"page":{"en":"https://aimap.page/en/benchmarks/model/qwen3-5-122b-a10b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/qwen3-5-122b-a10b/"},"best":{"lmarena-text":{"score":1416.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1360.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1226.4,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"mmlu-pro":{"score":86.7,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"qwen3-5-27b","name":"Qwen3.5-27B","provider":"Alibaba (Qwen)","openWeights":true,"release":null,"aliases":["qwen3.5-27b"],"page":{"en":"https://aimap.page/en/benchmarks/model/qwen3-5-27b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/qwen3-5-27b/"},"best":{"lmarena-text":{"score":1408.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1357.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1216.4,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"mmlu-pro":{"score":86.1,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"qwen3-5-9b","name":"Qwen3.5-9B","provider":"Alibaba (Qwen)","openWeights":true,"release":"2026-02-24","aliases":["qwen3.5-9B_none","Qwen3.5 9B","qwen3.5-9B"],"page":{"en":"https://aimap.page/en/benchmarks/model/qwen3-5-9b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/qwen3-5-9b/"},"best":{"gpqa-diamond":{"score":78.91,"unit":"%","sourceType":"independent","date":"2026-08-27","source":"https://epoch.ai/benchmarks"},"mmlu-pro":{"score":82.5,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"aime":{"score":61.67,"unit":"%","sourceType":"independent","date":"2026-08-27","source":"https://epoch.ai/benchmarks"},"terminal-bench":{"score":9.21,"unit":"%","sourceType":"official","date":"2026-03-02","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"}}},{"id":"qwen3-7-max","name":"Qwen3.7-Max","provider":"Alibaba (Qwen)","openWeights":false,"release":"2026-05-19","aliases":["qwen3.7-max-20260517","qwen3.7-max","Qwen3.7 Max"],"page":{"en":"https://aimap.page/en/benchmarks/model/qwen3-7-max/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/qwen3-7-max/"},"best":{"lmarena-webdev":{"score":1515.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"gpqa-diamond":{"score":90.91,"unit":"%","sourceType":"independent","date":"2026-08-07","source":"https://epoch.ai/benchmarks"},"swe-bench-verified":{"score":77.27,"unit":"%","sourceType":"independent","date":"2026-06-18","source":"https://epoch.ai/benchmarks"},"aime":{"score":95.56,"unit":"%","sourceType":"independent","date":"2026-08-07","source":"https://epoch.ai/benchmarks"}}},{"id":"tulu-3-t-lu-3-70b","name":"Tulu 3 (Tülu 3) 70B","provider":"Ai2","openWeights":true,"release":"2024-11-21","aliases":["Llama-3.1-Tulu-3-70B-DPO","allenai/Llama-3.1-Tulu-3-70B-DPO"],"page":{"en":"https://aimap.page/en/benchmarks/model/tulu-3-t-lu-3-70b/","zh-hans":"https://aimap.page/zh-hans/benchmarks/model/tulu-3-t-lu-3-70b/"},"best":{"open-llm-leaderboard":{"score":42.22,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"gpqa-diamond":{"score":46.28,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"aime":{"score":4.44,"unit":"%","sourceType":"independent","date":"2025-03-07","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":42.66,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"}}},{"id":"amazon-nova-micro","name":"Amazon Nova Micro","provider":"Amazon","openWeights":false,"release":"2024-12-03","aliases":["amazon-nova-micro-v1.0","amazon.nova-micro-v1:0","Amazon-Nova-Micro-v1:0 (FC)"],"page":null,"best":{"lmarena-text":{"score":1240.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"mmlu":{"score":70.8,"unit":"%","sourceType":"official","date":"2024-12-03","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"bfcl":{"score":22.29,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"claude-2-1","name":"Claude 2.1","provider":"Anthropic","openWeights":false,"release":"2023-11-21","aliases":["claude-2.1"],"page":null,"best":{"gpqa-diamond":{"score":32.95,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"mmlu":{"score":73.5,"unit":"%","sourceType":"official","date":"2023-11-21","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"aime":{"score":1.94,"unit":"%","sourceType":"independent","date":"2025-03-07","source":"https://epoch.ai/benchmarks"}}},{"id":"claude-fable-5-1-max","name":"claude-fable-5.1-max","provider":"Anthropic","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1500.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1743.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1287.7,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"deepseek-r1-distill-qwen-1-5b","name":"DeepSeek-R1-Distill-Qwen-1.5B","provider":"DeepSeek","openWeights":true,"release":"2025-01-20","aliases":["deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B"],"page":null,"best":{"open-llm-leaderboard":{"score":10.35,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"gpqa-diamond":{"score":33.59,"unit":"%","sourceType":"independent","date":"2026-08-28","source":"https://epoch.ai/benchmarks"},"aime":{"score":21.39,"unit":"%","sourceType":"independent","date":"2026-08-28","source":"https://epoch.ai/benchmarks"}}},{"id":"deepseek-r1-distill-qwen-32b","name":"DeepSeek-R1-Distill-Qwen-32B","provider":"DeepSeek","openWeights":true,"release":"2025-01-20","aliases":["deepseek-ai/DeepSeek-R1-Distill-Qwen-32B"],"page":null,"best":{"open-llm-leaderboard":{"score":22.96,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"gpqa-diamond":{"score":64.14,"unit":"%","sourceType":"independent","date":"2026-08-28","source":"https://epoch.ai/benchmarks"},"aime":{"score":55.56,"unit":"%","sourceType":"independent","date":"2026-08-28","source":"https://epoch.ai/benchmarks"}}},{"id":"deepseek-v3-2-exp","name":"DeepSeek-V3.2-Exp","provider":"DeepSeek","openWeights":true,"release":null,"aliases":["deepseek-v3.2-exp-thinking","deepseek-v3.2-exp","DeepSeek-V3.2-Exp (FC)"],"page":null,"best":{"lmarena-text":{"score":1424.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1272.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"bfcl":{"score":54.12,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"dolly-2-0-12b","name":"Dolly 2.0-12b","provider":"Databricks","openWeights":true,"release":"2023-04-11","aliases":["dolly-v2-12b","Dolly-v2-12B","databricks/dolly-v2-12b"],"page":null,"best":{"lmarena-text":{"score":982.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":6.37,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu":{"score":26.2,"unit":"%","sourceType":"paper","date":"2023-04-11","source":"http://arxiv.org/abs/2309.03450"}}},{"id":"gemini-2-0-flash-dec-2024","name":"Gemini 2.0 Flash (Dec 2024)","provider":"Google","openWeights":false,"release":"2024-12-11","aliases":["gemini-2.0-flash-exp","Gemini 2.0 Flash (Experimental)","CodeShellAgent + Gemini 2.0 Flash (Experimental)","Gemini-2.0-Flash-exp"],"page":null,"best":{"mmlu":{"score":79.7,"unit":"%","sourceType":"official","date":"2024-12-11","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"mmlu-pro":{"score":76.24,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"swe-bench-verified":{"score":44.2,"unit":"%","sourceType":"official","date":"2025-01-18","source":"https://www.swebench.com/#verified"}}},{"id":"gemini-2-0-flash-thinking-jan-2025","name":"Gemini 2.0 Flash Thinking (Jan 2025)","provider":"Google","openWeights":false,"release":"2025-01-21","aliases":["gemini-2.0-flash-thinking-exp-01-21","Gemini 2.0 Flash Thinking Exp","Gemini 2.0 Flash Thinking (January 2025)"],"page":null,"best":{"gpqa-diamond":{"score":57.07,"unit":"%","sourceType":"independent","date":"2025-02-06","source":"https://epoch.ai/benchmarks"},"aime":{"score":57.78,"unit":"%","sourceType":"independent","date":"2025-03-07","source":"https://epoch.ai/benchmarks"},"hle":{"score":6.56,"unit":"%","sourceType":"compiled","date":"2025-01-21","source":"https://epoch.ai/benchmarks"}}},{"id":"gemini-2-0-pro","name":"Gemini 2.0 Pro","provider":"Google","openWeights":false,"release":"2025-02-05","aliases":["gemini-2.0-pro-exp-02-05","Gemini 2.0 Pro Exp (Feb 2025)","Gemini-2.0-Pro"],"page":null,"best":{"gpqa-diamond":{"score":65.66,"unit":"%","sourceType":"independent","date":"2025-02-07","source":"https://epoch.ai/benchmarks"},"mmlu-pro":{"score":79.1,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"math-level-5":{"score":83.46,"unit":"%","sourceType":"independent","date":"2025-02-06","source":"https://epoch.ai/benchmarks"}}},{"id":"gemini-2-5-flash-apr-2025","name":"Gemini 2.5 Flash (Apr 2025)","provider":"Google","openWeights":false,"release":"2025-04-17","aliases":["gemini-2.5-flash-preview-04-17","Gemini 2.5 Flash Preview (Apr 2025)","Gemini 2.5 Flash (April 2025)","Gemini-2.5-Flash-04-17"],"page":null,"best":{"livecodebench":{"score":56.6,"unit":"%","sourceType":"official","date":"2025-04-07","source":"https://livecodebench.github.io/leaderboard.html"},"aime":{"score":73.06,"unit":"%","sourceType":"independent","date":"2025-04-22","source":"https://epoch.ai/benchmarks"},"hle":{"score":12.08,"unit":"%","sourceType":"compiled","date":"2025-04-17","source":"https://epoch.ai/benchmarks"}}},{"id":"gemini-2-5-flash-may-2025","name":"Gemini 2.5 Flash (May 2025)","provider":"Google","openWeights":false,"release":"2025-05-20","aliases":["gemini-2.5-flash-preview-05-20","Gemini 2.5 Flash Preview (May 2025)","Gemini-2.5-Flash-05-20"],"page":null,"best":{"livecodebench":{"score":59.3,"unit":"%","sourceType":"official","date":"2025-04-07","source":"https://livecodebench.github.io/leaderboard.html"},"aime":{"score":70.83,"unit":"%","sourceType":"independent","date":"2025-05-20","source":"https://epoch.ai/benchmarks"},"hle":{"score":10.96,"unit":"%","sourceType":"compiled","date":"2025-05-20","source":"https://epoch.ai/benchmarks"}}},{"id":"gemini-2-5-flash-sep-2025","name":"Gemini 2.5 Flash (Sep 2025)","provider":"Google","openWeights":false,"release":"2025-09-25","aliases":["gemini-2.5-flash-preview-09-2025"],"page":null,"best":{"lmarena-text":{"score":1403.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1230.3,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"terminal-bench":{"score":17.1,"unit":"%","sourceType":"official","date":"2025-11-03","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"}}},{"id":"gemini-3-1-flash-lite","name":"Gemini 3.1 Flash-Lite","provider":"Google","openWeights":false,"release":"2026-03-03","aliases":["gemini-3.1-flash-lite_minimal","gemini-3.1-flash-lite_high","gemini-3.1-flash-lite_low","gemini-3.1-flash-lite","gemini-3.1-flash-lite-preview"],"page":null,"best":{"gpqa-diamond":{"score":73.74,"unit":"%","sourceType":"independent","date":"2026-08-06","source":"https://epoch.ai/benchmarks"},"aime":{"score":37.78,"unit":"%","sourceType":"independent","date":"2026-08-06","source":"https://epoch.ai/benchmarks"},"hle":{"score":8.64,"unit":"%","sourceType":"compiled","date":"2026-03-03","source":"https://epoch.ai/benchmarks"}}},{"id":"gemini-2-0-flash-lite","name":"Gemini-2.0-Flash-Lite","provider":"Google","openWeights":false,"release":"2025-02-05","aliases":["gemini-2.0-flash-lite-preview-02-05"],"page":null,"best":{"lmarena-text":{"score":1353.6,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1136,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"mmlu-pro":{"score":71.6,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"gemma-1-1-2b-it","name":"gemma-1.1-2b-it","provider":"Google","openWeights":true,"release":null,"aliases":["google/gemma-1.1-2b-it"],"page":null,"best":{"lmarena-text":{"score":1116.6,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":8.05,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"humaneval":{"score":17.7,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"gemma-1-1-7b-it","name":"gemma-1.1-7b-it","provider":"Google","openWeights":true,"release":null,"aliases":["google/gemma-1.1-7b-it"],"page":null,"best":{"lmarena-text":{"score":1182.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":17.69,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"humaneval":{"score":35.4,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"gemma-2-2b-it","name":"Gemma-2-2B-it","provider":"Google","openWeights":true,"release":null,"aliases":["gemma-2-2b-it","google/gemma-2-2b-it"],"page":null,"best":{"lmarena-text":{"score":1200.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":17.05,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu-pro":{"score":15.6,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"gemma-2b-it","name":"gemma-2b-it","provider":"Google","openWeights":true,"release":null,"aliases":["google/gemma-2b-it"],"page":null,"best":{"lmarena-text":{"score":1093.6,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":7.49,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"humaneval":{"score":15.2,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"gemma-4-31b","name":"gemma-4-31b","provider":"Google","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1452.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1365.9,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1262.3,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"gemma-7b-it","name":"gemma-7b-it","provider":"Google","openWeights":true,"release":null,"aliases":["google/gemma-7b-it"],"page":null,"best":{"lmarena-text":{"score":1137.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":13.07,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"humaneval":{"score":25,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"glm-4-5-air","name":"GLM-4.5-Air","provider":"Zhipu AI (Z.ai)","openWeights":true,"release":"2025-07-20","aliases":["glm-4.5-air","glm-4p5-air"],"page":null,"best":{"lmarena-text":{"score":1373.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"mmlu-pro":{"score":81.4,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"hle":{"score":8.12,"unit":"%","sourceType":"compiled","date":"2025-07-20","source":"https://epoch.ai/benchmarks"}}},{"id":"glm-4-7-flash","name":"glm-4.7-flash_none","provider":"Zhipu AI (Z.ai)","openWeights":true,"release":null,"aliases":["glm-4.7-flash"],"page":null,"best":{"lmarena-text":{"score":1364.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"gpqa-diamond":{"score":45.14,"unit":"%","sourceType":"independent","date":"2026-08-30","source":"https://epoch.ai/benchmarks"},"aime":{"score":58.33,"unit":"%","sourceType":"independent","date":"2026-08-30","source":"https://epoch.ai/benchmarks"}}},{"id":"glm-5v-turbo","name":"glm-5v-turbo","provider":"Zhipu AI (Z.ai)","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1433.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1401,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1230.1,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"gpt-5-1-codex","name":"GPT-5.1-Codex","provider":"OpenAI","openWeights":false,"release":"2025-11-12","aliases":["gpt-5.1-codex","GPT-5.1 Codex","GPT 5.1 Codex","GPT 5.1 Codex (medium)"],"page":null,"best":{"lmarena-webdev":{"score":1337.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"swe-bench-verified":{"score":66,"unit":"%","sourceType":"official","date":"2025-11-24","source":"https://www.swebench.com/#verified"},"terminal-bench":{"score":57.8,"unit":"%","sourceType":"official","date":"2025-11-16","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"}}},{"id":"gpt-5-2-codex","name":"GPT-5.2 Codex","provider":"OpenAI","openWeights":false,"release":"2025-12-18","aliases":["gpt-5.2-codex","GPT-5.2-Codex","gpt-5-2-codex","GPT 5.2 Codex"],"page":null,"best":{"lmarena-webdev":{"score":1339.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"swe-bench-verified":{"score":72.8,"unit":"%","sourceType":"official","date":"2026-02-19","source":"https://www.swebench.com/#verified"},"terminal-bench":{"score":66.52,"unit":"%","sourceType":"official","date":"2026-01-14","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"}}},{"id":"gpt-6-astra-max","name":"gpt-6-astra-max","provider":"OpenAI","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1475.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1786.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1284.3,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"gpt-6-1-sol-max","name":"gpt-6.1-sol-max","provider":"OpenAI","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1483.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1755.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1290.6,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"gpt-j-6b","name":"GPT-J-6B","provider":"EleutherAI","openWeights":true,"release":"2021-08-05","aliases":["gpt-j-6b","EleutherAI/gpt-j-6b"],"page":null,"best":{"open-llm-leaderboard":{"score":6.57,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu":{"score":25.7,"unit":"%","sourceType":"paper","date":"2021-08-05","source":"http://arxiv.org/abs/2309.03450"},"humaneval":{"score":11,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"granite-3-1-2b-instruct","name":"Granite-3.1-2B-Instruct","provider":"IBM","openWeights":true,"release":null,"aliases":["granite-3.1-2b-instruct","ibm-granite/granite-3.1-2b-instruct"],"page":null,"best":{"lmarena-text":{"score":1178.9,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":21.71,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu-pro":{"score":31.97,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"granite-4-0-350m","name":"granite-4.0-350m","provider":"IBM","openWeights":true,"release":"2025-10-28","aliases":["Granite-4.0-350m (FC)"],"page":null,"best":{"gpqa-diamond":{"score":11.24,"unit":"%","sourceType":"independent","date":"2026-08-28","source":"https://epoch.ai/benchmarks"},"aime":{"score":0.28,"unit":"%","sourceType":"independent","date":"2026-08-28","source":"https://epoch.ai/benchmarks"},"bfcl":{"score":18.98,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"grok-3","name":"Grok 3","provider":"xAI","openWeights":false,"release":"2025-04-09","aliases":["grok-3-beta"],"page":null,"best":{"gpqa-diamond":{"score":75.76,"unit":"%","sourceType":"independent","date":"2025-05-26","source":"https://epoch.ai/benchmarks"},"aime":{"score":55.56,"unit":"%","sourceType":"independent","date":"2025-04-10","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":88.75,"unit":"%","sourceType":"independent","date":"2025-04-10","source":"https://epoch.ai/benchmarks"}}},{"id":"grok-4-fast","name":"Grok 4 fast","provider":"xAI","openWeights":false,"release":"2025-09-19","aliases":["grok-4-fast-reasoning"],"page":null,"best":{"lmarena-text":{"score":1405.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1159.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"}}},{"id":"grok-4-20","name":"Grok 4.20","provider":"xAI","openWeights":false,"release":"2026-02-17","aliases":["grok-4.20-0309-reasoning","grok-4-20","Grok 4.20 Reasoning"],"page":null,"best":{"gpqa-diamond":{"score":89.33,"unit":"%","sourceType":"independent","date":"2026-07-13","source":"https://epoch.ai/benchmarks"},"aime":{"score":92.22,"unit":"%","sourceType":"independent","date":"2026-07-13","source":"https://epoch.ai/benchmarks"},"terminal-bench":{"score":57.3,"unit":"%","sourceType":"official","date":"2026-03-10","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"}}},{"id":"grok-2-dec-2024","name":"Grok-2 (Dec 2024)","provider":"xAI","openWeights":false,"release":"2024-12-12","aliases":["grok-2-1212"],"page":null,"best":{"gpqa-diamond":{"score":53.79,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"aime":{"score":11.53,"unit":"%","sourceType":"independent","date":"2025-02-25","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":63.52,"unit":"%","sourceType":"independent","date":"2025-02-17","source":"https://epoch.ai/benchmarks"}}},{"id":"grok-4-20-beta-0309","name":"grok-4.20-beta-0309-reasoning","provider":"xAI","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1471.6,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1374.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1255.4,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"hermes-2-theta-llama-3-70b","name":"Hermes 2 Theta Llama-3 70B","provider":"Nous Research","openWeights":true,"release":"2024-06-20","aliases":["Hermes-2-Theta-Llama-3-70B"],"page":null,"best":{"gpqa-diamond":{"score":37.47,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"aime":{"score":2.5,"unit":"%","sourceType":"independent","date":"2025-04-01","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":22.69,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"}}},{"id":"jamba-1-5-large","name":"Jamba 1.5 Large","provider":"AI21 Labs","openWeights":true,"release":null,"aliases":["jamba-1.5-large","Jamba-1.5-Large"],"page":null,"best":{"lmarena-text":{"score":1289.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"mmlu":{"score":78.2,"unit":"%","sourceType":"official","date":"","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"mmlu-pro":{"score":49.46,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"kimi-k2-7-code","name":"Kimi K2.7 Code","provider":"Moonshot AI","openWeights":true,"release":"2026-06-12","aliases":["kimi-k2.7-code"],"page":null,"best":{"lmarena-webdev":{"score":1473.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"gpqa-diamond":{"score":87.88,"unit":"%","sourceType":"independent","date":"2026-08-07","source":"https://epoch.ai/benchmarks"},"aime":{"score":95.56,"unit":"%","sourceType":"independent","date":"2026-08-07","source":"https://epoch.ai/benchmarks"}}},{"id":"kimi-k3","name":"Kimi K3","provider":"Moonshot AI","openWeights":true,"release":"2026-07-16","aliases":["kimi-k3_low","Kimi K3 (low)","kimi-k3_high","Kimi K3 (high)","kimi-k3_max","Kimi K3 (max)"],"page":null,"best":{"gpqa-diamond":{"score":93.12,"unit":"%","sourceType":"independent","date":"2026-07-16","source":"https://epoch.ai/benchmarks"},"aime":{"score":97.22,"unit":"%","sourceType":"independent","date":"2026-07-16","source":"https://epoch.ai/benchmarks"}}},{"id":"llama-2-13b","name":"Llama 2-13B","provider":"Meta","openWeights":true,"release":"2023-07-18","aliases":["llama-2-13b-chat","Llama-2-13b","Llama 2 (13B)","LLAMA 2 13B","LLaMA 2 13B    ","LLaMA 2-13B","LLaMA-2 13B","Llama-2-13b-chat","LLaMA2-Chat 13B","Llama-2-13B"],"page":null,"best":{"lmarena-text":{"score":1141.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"mmlu":{"score":55.4,"unit":"%","sourceType":"official","date":"2023-07-18","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"mmlu-pro":{"score":25.34,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"llama-2-7b","name":"Llama 2-7B","provider":"Meta","openWeights":true,"release":"2023-07-18","aliases":["llama-2-7b-chat","Llama-2-7b","Llama 2 (7B)","LLAMA 2 7B","LLaMA 2 7B     ","LLaMA 2-7B","LLaMA-2 7B","Llama2-7B","Llama-2-7B"],"page":null,"best":{"lmarena-text":{"score":1107.9,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"mmlu":{"score":45.8,"unit":"%","sourceType":"official","date":"2023-07-18","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"mmlu-pro":{"score":20.32,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"mimo-v2-5","name":"MiMo-V2.5","provider":"Xiaomi Corp","openWeights":true,"release":"2026-04-23","aliases":["mimo-v2.5"],"page":null,"best":{"lmarena-text":{"score":1433.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1438.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1233.2,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"mimo-v2-6-flash","name":"MiMo-V2.6 Flash","provider":"Xiaomi Corp","openWeights":true,"release":"2026-09-21","aliases":["mimo-v2.6-flash"],"page":null,"best":{"lmarena-text":{"score":1450.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1636.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1247.5,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"mimo-v2-6-pro","name":"MiMo-V2.6 Pro","provider":"Xiaomi Corp","openWeights":true,"release":"2026-09-21","aliases":["mimo-v2.6-pro"],"page":null,"best":{"lmarena-text":{"score":1480.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1629,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1245.2,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"minimax-m2-7","name":"MiniMax-M2.7","provider":"MiniMax","openWeights":true,"release":"2026-03-18","aliases":["minimax-m2.7","MiniMax M2.7","MiniMax M2.7 Highspeed"],"page":null,"best":{"lmarena-text":{"score":1415,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1397.9,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"terminal-bench":{"score":45.06,"unit":"%","sourceType":"official","date":"2026-03-18","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"}}},{"id":"mistral-7b-v0-1","name":"Mistral 7B v0.1","provider":"Mistral AI","openWeights":true,"release":"2023-09-27","aliases":["Mistral-7B-v0.1","Mistral 7B","Mistral 7b             ","Mistral v0.1 (7B)","Mistral-7B-Instruct-v0.1","mistralai/Mistral-7B-v0.1","mistralai/Mistral-7B-Instruct-v0.1"],"page":null,"best":{"open-llm-leaderboard":{"score":14.58,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu":{"score":56.6,"unit":"%","sourceType":"official","date":"2023-09-27","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"mmlu-pro":{"score":30.88,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"mistral-small-3","name":"Mistral Small 3","provider":"Mistral AI","openWeights":true,"release":"2025-01-25","aliases":["mistral-small-3-2501","mistral-small-2501"],"page":null,"best":{"gpqa-diamond":{"score":47.29,"unit":"%","sourceType":"independent","date":"2026-08-30","source":"https://epoch.ai/benchmarks"},"aime":{"score":6.67,"unit":"%","sourceType":"independent","date":"2026-08-30","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":44.82,"unit":"%","sourceType":"independent","date":"2025-01-30","source":"https://epoch.ai/benchmarks"}}},{"id":"mistral-small-3-1","name":"Mistral Small 3.1","provider":"Mistral AI","openWeights":true,"release":"2025-03-17","aliases":["mistral-small-3.1-2503","mistral-small-2503"],"page":null,"best":{"gpqa-diamond":{"score":41.92,"unit":"%","sourceType":"independent","date":"2026-08-30","source":"https://epoch.ai/benchmarks"},"aime":{"score":3.89,"unit":"%","sourceType":"independent","date":"2026-08-30","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":46.77,"unit":"%","sourceType":"independent","date":"2025-03-18","source":"https://epoch.ai/benchmarks"}}},{"id":"mistral-large-3","name":"mistral-large-3","provider":"Mistral AI","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1413.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1230.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1200.6,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"mistral-medium-3-5","name":"mistral-medium-3.5","provider":"Mistral AI","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1426.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1263.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1199.5,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"muse-spark-1-2","name":"muse-spark-1.2 (xHigh)","provider":"Meta","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1492,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1532.6,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1292.8,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"muse-spark-1-3-max","name":"muse-spark-1.3-max","provider":"Meta","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1494.2,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1656.9,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1290.2,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"phi-3-small-7-4b","name":"phi-3-small 7.4B","provider":"Microsoft","openWeights":true,"release":"2024-04-23","aliases":["phi-3-small-8k-instruct","Phi-3-small-8k-instruct","Phi-3-small","microsoft/Phi-3-small-8k-instruct"],"page":null,"best":{"lmarena-text":{"score":1171.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":32.34,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu":{"score":75.7,"unit":"%","sourceType":"paper","date":"2024-04-23","source":"http://arxiv.org/abs/2404.14219"}}},{"id":"qwen-3-6-35b-a3b","name":"Qwen 3.6 35B-A3B","provider":"Alibaba (Qwen)","openWeights":true,"release":"2026-04-14","aliases":["qwen3.6-35b-a3b","Qwen3.6 35B-A3B","qwen3.6-35b-a3b_none","Qwen3.6-35B-A3B"],"page":null,"best":{"gpqa-diamond":{"score":83.84,"unit":"%","sourceType":"independent","date":"2026-08-07","source":"https://epoch.ai/benchmarks"},"aime":{"score":86.67,"unit":"%","sourceType":"independent","date":"2026-08-07","source":"https://epoch.ai/benchmarks"},"terminal-bench":{"score":24.63,"unit":"%","sourceType":"official","date":"2026-04-16","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"}}},{"id":"qwen-3-8-27b","name":"Qwen 3.8 27B","provider":"Alibaba (Qwen)","openWeights":true,"release":"2026-08-14","aliases":["qwen3.8-27b"],"page":null,"best":{"lmarena-text":{"score":1438.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1592.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1242.8,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"qwen-plus-jan-2025","name":"Qwen Plus (Jan 2025)","provider":"Alibaba (Qwen)","openWeights":false,"release":"2025-01-25","aliases":["qwen-plus-2025-01-25"],"page":null,"best":{"gpqa-diamond":{"score":48.11,"unit":"%","sourceType":"independent","date":"2025-04-07","source":"https://epoch.ai/benchmarks"},"aime":{"score":17.78,"unit":"%","sourceType":"independent","date":"2025-04-07","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":65.28,"unit":"%","sourceType":"independent","date":"2025-04-07","source":"https://epoch.ai/benchmarks"}}},{"id":"qwen-turbo","name":"Qwen-Turbo","provider":"Alibaba (Qwen)","openWeights":false,"release":"2024-11-01","aliases":["qwen-turbo-2024-11-01"],"page":null,"best":{"gpqa-diamond":{"score":41.79,"unit":"%","sourceType":"independent","date":"2025-04-07","source":"https://epoch.ai/benchmarks"},"aime":{"score":6.11,"unit":"%","sourceType":"independent","date":"2025-04-07","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":56.23,"unit":"%","sourceType":"independent","date":"2025-04-07","source":"https://epoch.ai/benchmarks"}}},{"id":"qwen2-5-14b","name":"Qwen2.5-14B","provider":"Alibaba (Qwen)","openWeights":true,"release":"2024-09-19","aliases":["qwen2.5-14b-instruct","Qwen2.5 14b instruct","Qwen/Qwen2.5-14B-Instruct","Qwen/Qwen2.5-14B"],"page":null,"best":{"open-llm-leaderboard":{"score":41.31,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu":{"score":79.9,"unit":"%","sourceType":"paper","date":"2024-09-19","source":"http://arxiv.org/abs/2412.08905"},"mmlu-pro":{"score":63.69,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"qwen3-1-7b","name":"Qwen3-1.7B","provider":"Alibaba (Qwen)","openWeights":true,"release":"2025-04-29","aliases":["qwen3-1.7b_none","qwen3-1.7b","Qwen3-1.7B (FC)"],"page":null,"best":{"gpqa-diamond":{"score":30.62,"unit":"%","sourceType":"independent","date":"2026-08-28","source":"https://epoch.ai/benchmarks"},"aime":{"score":8.06,"unit":"%","sourceType":"independent","date":"2026-08-28","source":"https://epoch.ai/benchmarks"},"bfcl":{"score":28.41,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"qwen3-14b","name":"Qwen3-14B","provider":"Alibaba (Qwen)","openWeights":true,"release":"2025-04-29","aliases":["qwen3-14b_none","qwen3-14b","Qwen3-14B (FC)","Qwen3-14B (Prompt)"],"page":null,"best":{"gpqa-diamond":{"score":53.41,"unit":"%","sourceType":"independent","date":"2026-08-28","source":"https://epoch.ai/benchmarks"},"aime":{"score":25.83,"unit":"%","sourceType":"independent","date":"2026-08-30","source":"https://epoch.ai/benchmarks"},"bfcl":{"score":41.03,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"qwen3-235b-a22b-instruct-jul-2025","name":"Qwen3-235B-A22B-Instruct (Jul 2025)","provider":"Alibaba (Qwen)","openWeights":true,"release":"2025-07-25","aliases":["qwen3-235b-a22b-instruct-2507","Qwen3-235B-A22B-Instruct-2507 (Prompt)","Qwen3-235B-A22B-Instruct-2507 (FC)","Qwen3-235B-A22B-Instruct-2507"],"page":null,"best":{"lmarena-text":{"score":1422.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"mmlu-pro":{"score":83,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"bfcl":{"score":52.15,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"qwen3-30b-a3b-thinking-jul-2025","name":"Qwen3-30B-A3B-Thinking (Jul 2025)","provider":"Alibaba (Qwen)","openWeights":true,"release":"2025-07-30","aliases":["qwen3-30b-a3b-thinking-2507","Qwen3-30B-A3B-Thinking-2507"],"page":null,"best":{"gpqa-diamond":{"score":70.08,"unit":"%","sourceType":"independent","date":"2026-08-30","source":"https://epoch.ai/benchmarks"},"mmlu-pro":{"score":80.9,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"aime":{"score":70.28,"unit":"%","sourceType":"independent","date":"2026-08-30","source":"https://epoch.ai/benchmarks"}}},{"id":"qwen3-4b-instruct-2507","name":"qwen3-4b-instruct-2507","provider":"Alibaba (Qwen)","openWeights":true,"release":"2025-08-06","aliases":["Qwen3-4B-Instruct-2507 (FC)","Qwen3-4B-Instruct-2507 (Prompt)"],"page":null,"best":{"gpqa-diamond":{"score":45.83,"unit":"%","sourceType":"independent","date":"2026-08-28","source":"https://epoch.ai/benchmarks"},"aime":{"score":52.22,"unit":"%","sourceType":"independent","date":"2026-08-28","source":"https://epoch.ai/benchmarks"},"bfcl":{"score":35.68,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"qwen3-8b","name":"Qwen3-8B","provider":"Alibaba (Qwen)","openWeights":true,"release":"2025-04-28","aliases":["qwen3-8b_none","qwen3-8b","Qwen3-8B (FC)","Qwen3-8B (Prompt)"],"page":null,"best":{"gpqa-diamond":{"score":47.47,"unit":"%","sourceType":"independent","date":"2026-08-27","source":"https://epoch.ai/benchmarks"},"aime":{"score":22.22,"unit":"%","sourceType":"independent","date":"2026-08-27","source":"https://epoch.ai/benchmarks"},"bfcl":{"score":42.57,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"qwen3-8-max-0902","name":"Qwen3.8 Max (0902)","provider":"Alibaba (Qwen)","openWeights":false,"release":"2026-09-01","aliases":["qwen3.8-max-0902","qwen3.8-max-0902_xhigh","Qwen3.8 Max (0902) (xhigh)"],"page":null,"best":{"lmarena-webdev":{"score":1673.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"gpqa-diamond":{"score":92.3,"unit":"%","sourceType":"independent","date":"2026-09-02","source":"https://epoch.ai/benchmarks"},"aime":{"score":100,"unit":"%","sourceType":"independent","date":"2026-09-02","source":"https://epoch.ai/benchmarks"}}},{"id":"qwq-32b-preview","name":"QwQ-32B-Preview","provider":"Alibaba (Qwen)","openWeights":true,"release":"2024-11-28","aliases":["qwq-32b-preview","Qwen/QwQ-32B-Preview"],"page":null,"best":{"lmarena-text":{"score":1154.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":34.12,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu-pro":{"score":70.97,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"seed-oss-36b-instruct","name":"seed-oss-36b-instruct","provider":"ByteDance","openWeights":null,"release":"2025-08-20","aliases":["Seed-OSS-36B-Instruct"],"page":null,"best":{"gpqa-diamond":{"score":71.53,"unit":"%","sourceType":"independent","date":"2026-08-30","source":"https://epoch.ai/benchmarks"},"mmlu-pro":{"score":82.7,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"aime":{"score":67.5,"unit":"%","sourceType":"independent","date":"2026-08-28","source":"https://epoch.ai/benchmarks"}}},{"id":"solar-10-7b-instruct-v1-0","name":"solar-10.7b-instruct-v1.0","provider":"upstage","openWeights":true,"release":null,"aliases":["SOLAR-10.7B-Instruct-v1.0","upstage/SOLAR-10.7B-Instruct-v1.0"],"page":null,"best":{"lmarena-text":{"score":1152.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":20.57,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"humaneval":{"score":37.2,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"step-5-preview","name":"Step 5 Preview","provider":"StepFun","openWeights":false,"release":null,"aliases":["step-5-preview-high"],"page":null,"best":{"lmarena-text":{"score":1447.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1563.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"lmarena-vision":{"score":1259.7,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"vicuna-13b","name":"Vicuna-13B","provider":"LMSYS","openWeights":true,"release":null,"aliases":["vicuna-13b"],"page":null,"best":{"lmarena-text":{"score":1141.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"mmlu":{"score":52,"unit":"%","sourceType":"paper","date":"","source":"http://arxiv.org/abs/2309.10305"},"humaneval":{"score":15.9,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"wizardlm-2-8x22b","name":"WizardLM-2 8x22B","provider":"Microsoft","openWeights":true,"release":"2024-04-15","aliases":["WizardLM-2-8x22B"],"page":null,"best":{"gpqa-diamond":{"score":43.43,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"mmlu-pro":{"score":39.24,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"math-level-5":{"score":25.74,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"}}},{"id":"yi-6b","name":"Yi 6B","provider":"01.AI","openWeights":true,"release":"2023-11-02","aliases":["Yi-6B","Yi (6B)","Yi-6B-Chat","Yi-Chat 6B","01-ai/Yi-6B-Chat","01-ai/Yi-6B","01-ai/Yi-6B-200K"],"page":null,"best":{"open-llm-leaderboard":{"score":14.12,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu":{"score":64,"unit":"%","sourceType":"official","date":"2023-11-02","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"mmlu-pro":{"score":28.84,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"athene-v2-chat","name":"Athene-V2-Chat","provider":"Nexusflow","openWeights":true,"release":null,"aliases":["athene-v2-chat"],"page":null,"best":{"lmarena-text":{"score":1314.2,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"mmlu-pro":{"score":70.21,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"aya-expanse-32b","name":"Aya-Expanse-32B","provider":"Cohere","openWeights":true,"release":null,"aliases":["CohereForAI/aya-expanse-32b"],"page":null,"best":{"open-llm-leaderboard":{"score":29.72,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu-pro":{"score":45.41,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"aya-expanse-8b","name":"Aya-Expanse-8B","provider":"Cohere","openWeights":true,"release":null,"aliases":["CohereForAI/aya-expanse-8b"],"page":null,"best":{"open-llm-leaderboard":{"score":22.41,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu-pro":{"score":33.74,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"c4ai-command-r-v01","name":"c4ai-command-r-v01","provider":"Cohere","openWeights":true,"release":null,"aliases":["CohereForAI/c4ai-command-r-v01"],"page":null,"best":{"open-llm-leaderboard":{"score":25.93,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu-pro":{"score":37.9,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"chatglm-6b","name":"chatglm-6b","provider":"Zhipu AI (Z.ai)","openWeights":true,"release":null,"aliases":["ChatGLM-6B"],"page":null,"best":{"lmarena-text":{"score":995.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"c-eval":{"score":34.5,"unit":"%","sourceType":"official","date":"2023-05-15","source":"https://github.com/hkust-nlp/ceval#leaderboard"}}},{"id":"chatglm2-6b","name":"chatglm2-6b","provider":"Zhipu AI (Z.ai)","openWeights":true,"release":"2023-06-24","aliases":["ChatGLM2 6B"],"page":null,"best":{"lmarena-text":{"score":1024.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"mmlu":{"score":47.9,"unit":"%","sourceType":"paper","date":"2023-06-24","source":"https://arxiv.org/pdf/2309.16609"}}},{"id":"chatgpt-4o-latest","name":"chatgpt-4o-latest","provider":"OpenAI","openWeights":false,"release":null,"aliases":["chatgpt-4o-latest-20250326"],"page":null,"best":{"lmarena-text":{"score":1442.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1238.8,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"claude-fable-5-1","name":"Claude Fable 5.1","provider":"Anthropic","openWeights":false,"release":"2026-09-01","aliases":["claude-fable-5-1_max","Claude Fable 5.1 (max)","claude-fable-5-1_xhigh","Claude Fable 5.1 (xhigh)","Fable 5.1 (xhigh)"],"page":null,"best":{"aime":{"score":100,"unit":"%","sourceType":"independent","date":"2026-09-01","source":"https://epoch.ai/benchmarks"},"hle":{"score":46.5,"unit":"%","sourceType":"compiled","date":"2026-09-01","source":"https://epoch.ai/benchmarks"}}},{"id":"claude-4-5-opus","name":"claude-4-5-opus","provider":"Anthropic","openWeights":null,"release":null,"aliases":["Claude 4.5 Opus","Claude 4.5 Opus (high)","Claude-4.5-Opus(Thinking)"],"page":null,"best":{"mmlu-pro":{"score":87.3,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"swe-bench-verified":{"score":76.8,"unit":"%","sourceType":"official","date":"2026-02-17","source":"https://www.swebench.com/#verified"}}},{"id":"claude-4-opus","name":"claude-4-opus","provider":"Anthropic","openWeights":null,"release":null,"aliases":["claude-4-opus-20250514","Claude 4 Opus","Tools + Claude 4 Opus (2025-05-22)","Claude 4 Opus (20250514)","Claude-4-Opus-Thinking"],"page":null,"best":{"mmlu-pro":{"score":87.3,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"swe-bench-verified":{"score":73.2,"unit":"%","sourceType":"official","date":"2025-05-22","source":"https://www.swebench.com/#verified"}}},{"id":"claude-4-sonnet","name":"claude-4-sonnet","provider":"Anthropic","openWeights":null,"release":null,"aliases":["claude-4-sonnet-20250514","Claude 4 Sonnet","Lingxi-v1.5_claude-4-sonnet-20250514","Tools + Claude 4 Sonnet (2025-05-22)","Bloop","Moatless Tools + Claude 4 Sonnet","OpenHands + Claude 4 Sonnet","SWE-agent + Claude 4 Sonnet","Claude 4 Sonnet (20250514)","Claude-4-Sonnet"],"page":null,"best":{"mmlu-pro":{"score":83.7,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"swe-bench-verified":{"score":74.6,"unit":"%","sourceType":"official","date":"2025-07-20","source":"https://www.swebench.com/#verified"}}},{"id":"claude-opus-5-max","name":"claude-opus-5-max","provider":"Anthropic","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1489.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1691.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"}}},{"id":"codellama-70b-instruct","name":"codellama-70b-instruct","provider":"Meta","openWeights":true,"release":null,"aliases":["CodeLlama-70B-Instruct"],"page":null,"best":{"lmarena-text":{"score":1119.2,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"humaneval":{"score":65.9,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"codeqwen1-5-7b","name":"CodeQwen1.5-7B","provider":"Alibaba (Qwen)","openWeights":true,"release":"2024-04-15","aliases":[],"page":null,"best":{"mmlu":{"score":40.5,"unit":"%","sourceType":"paper","date":"2024-04-15","source":"http://arxiv.org/abs/2409.12186"},"humaneval":{"score":45.7,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"codestral-22b-v0-1","name":"Codestral-22B-v0.1","provider":"Mistral AI","openWeights":true,"release":null,"aliases":["mistralai/Codestral-22B-v0.1"],"page":null,"best":{"open-llm-leaderboard":{"score":23.28,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"humaneval":{"score":73.8,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"deepseek-coder-1-3b","name":"DeepSeek Coder 1.3B","provider":"DeepSeek","openWeights":true,"release":"2023-11-02","aliases":["deepseek-coder-1.3b-base","DS-Coder-1.3B-Base","DeepSeek-Coder-1.3B-base","DeepSeek-Coder-1.3B-instruct"],"page":null,"best":{"mmlu":{"score":25.8,"unit":"%","sourceType":"paper","date":"2023-11-02","source":"http://arxiv.org/abs/2409.12186"},"humaneval":{"score":25.6,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"deepseek-coder-33b","name":"DeepSeek Coder 33B","provider":"DeepSeek","openWeights":true,"release":"2023-11-02","aliases":["deepseek-coder-33b-base","DS-Coder-33B-Base","DeepSeek-Coder-33B-base","DeepSeek-Coder-33B-instruct"],"page":null,"best":{"mmlu":{"score":39.4,"unit":"%","sourceType":"paper","date":"2023-11-02","source":"http://arxiv.org/abs/2409.12186"},"humaneval":{"score":44.5,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"deepseek-coder-6-7b","name":"DeepSeek Coder 6.7B","provider":"DeepSeek","openWeights":true,"release":"2023-11-02","aliases":["deepseek-coder-6.7b-base","DS-Coder-6.7B-Base","DeepSeek-Coder-6.7B-base","DeepSeek-Coder-6.7B-instruct"],"page":null,"best":{"mmlu":{"score":36.4,"unit":"%","sourceType":"paper","date":"2023-11-02","source":"http://arxiv.org/abs/2409.12186"},"humaneval":{"score":39.6,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","provider":"DeepSeek","openWeights":true,"release":"2026-07-31","aliases":["deepseek-v4-flash-0731_max","DeepSeek V4 Flash 0731 (max)"],"page":null,"best":{"gpqa-diamond":{"score":91.04,"unit":"%","sourceType":"independent","date":"2026-08-02","source":"https://epoch.ai/benchmarks"},"aime":{"score":94.44,"unit":"%","sourceType":"independent","date":"2026-08-02","source":"https://epoch.ai/benchmarks"}}},{"id":"deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","provider":"DeepSeek","openWeights":true,"release":"2026-08-13","aliases":["deepseek-v4-pro-0813_max","DeepSeek V4 Pro 0813 (max)"],"page":null,"best":{"gpqa-diamond":{"score":91.67,"unit":"%","sourceType":"independent","date":"2026-08-18","source":"https://epoch.ai/benchmarks"},"aime":{"score":98.61,"unit":"%","sourceType":"independent","date":"2026-08-18","source":"https://epoch.ai/benchmarks"}}},{"id":"deepseek-v4-1-flash","name":"DeepSeek V4.1 Flash","provider":"DeepSeek","openWeights":true,"release":"2026-09-09","aliases":["deepseek-v4.1-flash_max","DeepSeek V4.1 Flash (max)"],"page":null,"best":{"gpqa-diamond":{"score":89.84,"unit":"%","sourceType":"independent","date":"2026-10-09","source":"https://epoch.ai/benchmarks"},"aime":{"score":98.33,"unit":"%","sourceType":"independent","date":"2026-10-08","source":"https://epoch.ai/benchmarks"}}},{"id":"deepseek-v4-1-flash-1017","name":"DeepSeek V4.1 Flash 1017","provider":"DeepSeek","openWeights":true,"release":"2026-10-17","aliases":["deepseek-v4.1-flash-1017_max","DeepSeek V4.1 Flash 1017 (max)"],"page":null,"best":{"gpqa-diamond":{"score":93.18,"unit":"%","sourceType":"independent","date":"2026-10-19","source":"https://epoch.ai/benchmarks"},"aime":{"score":99.44,"unit":"%","sourceType":"independent","date":"2026-10-19","source":"https://epoch.ai/benchmarks"}}},{"id":"deepseek-coder-v2-236b","name":"DeepSeek-Coder-V2 236B","provider":"DeepSeek","openWeights":true,"release":"2024-06-17","aliases":["DeepSeek-Coder-V2-Instruct"],"page":null,"best":{"mmlu-pro":{"score":63.63,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"humaneval":{"score":82.3,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"deepseek-coder-v2-lite-base","name":"DeepSeek-Coder-V2-Lite-Base","provider":"DeepSeek","openWeights":null,"release":"2024-06-13","aliases":["DS-Coder-V2-Lite-Base"],"page":null,"best":{"mmlu":{"score":60.5,"unit":"%","sourceType":"paper","date":"2024-06-13","source":"http://arxiv.org/abs/2409.12186"},"mmlu-pro":{"score":34.37,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"deepseek-r1-0528-qwen3-8b","name":"deepseek-r1-0528-qwen3-8b","provider":"DeepSeek","openWeights":null,"release":"2025-05-29","aliases":[],"page":null,"best":{"gpqa-diamond":{"score":9.28,"unit":"%","sourceType":"independent","date":"2026-08-28","source":"https://epoch.ai/benchmarks"},"aime":{"score":43.89,"unit":"%","sourceType":"independent","date":"2026-08-28","source":"https://epoch.ai/benchmarks"}}},{"id":"deepseek-v3-1","name":"DeepSeek-V3.1-Thinking","provider":"DeepSeek","openWeights":true,"release":null,"aliases":["deepseek-v3.1","deepseek-v3.1-thinking"],"page":null,"best":{"lmarena-text":{"score":1417.2,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"mmlu-pro":{"score":84.8,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"deepseek-v4-flash","name":"deepseek-v4-flash","provider":"DeepSeek","openWeights":true,"release":null,"aliases":["deepseek-v4-flash-high"],"page":null,"best":{"lmarena-text":{"score":1436,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1581.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"}}},{"id":"deepseek-v4-flash-high-preview","name":"deepseek-v4-flash-high-preview","provider":"DeepSeek","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1438.6,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1430.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"}}},{"id":"deepseek-v4-pro-high-preview","name":"deepseek-v4-pro-high-preview","provider":"DeepSeek","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1454.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1463.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"}}},{"id":"deepseek-v4-1-flash-max","name":"deepseek-v4.1-flash-max","provider":"DeepSeek","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1474.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1618.6,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"}}},{"id":"dola-seed-2-0-pro","name":"dola-seed-2.0-pro","provider":"ByteDance","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1456.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1256.6,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"exaone-3-5-2-4b-instruct","name":"EXAONE-3.5-2.4B-Instruct","provider":"LGAI-EXAONE","openWeights":true,"release":null,"aliases":["LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":27.14,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu-pro":{"score":39.1,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"exaone-3-5-32b-instruct","name":"EXAONE-3.5-32B-Instruct","provider":"LGAI-EXAONE","openWeights":true,"release":null,"aliases":["LGAI-EXAONE/EXAONE-3.5-32B-Instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":37.6,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu-pro":{"score":58.91,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"exaone-3-5-7-8b-instruct","name":"EXAONE-3.5-7.8B-Instruct","provider":"LGAI-EXAONE","openWeights":true,"release":null,"aliases":["LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":32.55,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu-pro":{"score":46.24,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"falcon-2-11b","name":"Falcon 2 11B","provider":"Technology Innovation Institute","openWeights":true,"release":"2024-05-09","aliases":["falcon-11b","Falcon 2-11B","Falcon2-11B","tiiuae/falcon-11B"],"page":null,"best":{"open-llm-leaderboard":{"score":13.85,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu":{"score":58.4,"unit":"%","sourceType":"paper","date":"2024-05-09","source":"http://arxiv.org/abs/2407.14885"}}},{"id":"falcon-40b","name":"Falcon-40B","provider":"Technology Innovation Institute","openWeights":true,"release":"2023-03-15","aliases":["falcon-40b","Falcon 40B","tiiuae/falcon-40b","tiiuae/falcon-40b-instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":11.4,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu":{"score":56.9,"unit":"%","sourceType":"paper","date":"2023-03-15","source":"http://arxiv.org/abs/2407.14885"}}},{"id":"falcon-7b","name":"Falcon-7B","provider":"Technology Innovation Institute","openWeights":true,"release":"2023-04-24","aliases":["falcon-7b","Falcon 7B","tiiuae/falcon-7b"],"page":null,"best":{"open-llm-leaderboard":{"score":5.17,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu":{"score":35,"unit":"%","sourceType":"paper","date":"2023-04-24","source":"http://arxiv.org/abs/2407.14885"}}},{"id":"falcon3-10b-instruct","name":"Falcon3-10B-Instruct","provider":"TII UAE","openWeights":true,"release":null,"aliases":["Falcon3-10B-Instruct (FC)","tiiuae/Falcon3-10B-Instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":35.48,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"bfcl":{"score":27.01,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"falcon3-1b-instruct","name":"Falcon3-1B-Instruct","provider":"TII UAE","openWeights":true,"release":null,"aliases":["Falcon3-1B-Instruct (FC)","tiiuae/Falcon3-1B-Instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":16.16,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"bfcl":{"score":11.08,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"falcon3-3b-instruct","name":"Falcon3-3B-Instruct","provider":"TII UAE","openWeights":true,"release":null,"aliases":["Falcon3-3B-Instruct (FC)","tiiuae/Falcon3-3B-Instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":26.6,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"bfcl":{"score":16.25,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"falcon3-7b-instruct","name":"Falcon3-7B-Instruct","provider":"TII UAE","openWeights":true,"release":null,"aliases":["Falcon3-7B-Instruct (FC)","tiiuae/Falcon3-7B-Instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":36.4,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"bfcl":{"score":24.03,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"gemini-2-5-flash-lite-jun-2025","name":"Gemini 2.5 Flash-Lite (Jun 2025)","provider":"Google","openWeights":false,"release":"2025-06-17","aliases":["gemini-2.5-flash-lite-preview-06-17-thinking"],"page":null,"best":{"lmarena-text":{"score":1374.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1188.4,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"gemini-2-0-flash","name":"gemini-2.0-flash","provider":"Google","openWeights":null,"release":null,"aliases":["Gemini 2.0 Flash","Gemini-2.0-Flash"],"page":null,"best":{"mmlu-pro":{"score":77.6,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"swe-bench-verified":{"score":13.52,"unit":"%","sourceType":"official","date":"2025-07-26","source":"https://www.swebench.com/#verified"}}},{"id":"gemini-2-5-flash-lite-preview-09-2025-no","name":"gemini-2.5-flash-lite-preview-09-2025-no-thinking","provider":"Google","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1379.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1174.5,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"gemma-4-31b-it","name":"Gemma 4 31B IT","provider":"Google","openWeights":true,"release":"2026-04-02","aliases":["gemma-4-31b-it_minimal"],"page":null,"best":{"gpqa-diamond":{"score":75.76,"unit":"%","sourceType":"independent","date":"2026-08-06","source":"https://epoch.ai/benchmarks"},"aime":{"score":73.33,"unit":"%","sourceType":"independent","date":"2026-08-06","source":"https://epoch.ai/benchmarks"}}},{"id":"glm-4-9b","name":"GLM-4-9B","provider":"Zhipu AI (Z.ai)","openWeights":true,"release":null,"aliases":["THUDM/glm-4-9b"],"page":null,"best":{"open-llm-leaderboard":{"score":18.01,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu-pro":{"score":47.92,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"glm-4-9b-chat","name":"GLM-4-9B-Chat","provider":"Zhipu AI (Z.ai)","openWeights":true,"release":null,"aliases":["THUDM/glm-4-9b-chat"],"page":null,"best":{"open-llm-leaderboard":{"score":10.97,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu-pro":{"score":48.01,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"glm-4-5v","name":"glm-4.5v","provider":"Zhipu AI (Z.ai)","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1352,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1152.7,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"glm-4-6v","name":"glm-4.6v","provider":"Zhipu AI (Z.ai)","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1378.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1161.5,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"glm-5-2-max","name":"glm-5.2-max","provider":"Zhipu AI (Z.ai)","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1475.2,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1603.2,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"}}},{"id":"glm-5-3","name":"GLM-5.3","provider":"Zhipu AI (Z.ai)","openWeights":true,"release":"2026-08-14","aliases":["glm-5.3_max","GLM-5.3 (max)"],"page":null,"best":{"gpqa-diamond":{"score":90.91,"unit":"%","sourceType":"independent","date":"2026-08-24","source":"https://epoch.ai/benchmarks"},"aime":{"score":91.11,"unit":"%","sourceType":"independent","date":"2026-08-24","source":"https://epoch.ai/benchmarks"}}},{"id":"glm-5-3-max","name":"glm-5.3-max","provider":"Zhipu AI (Z.ai)","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1478.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1622.2,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"}}},{"id":"gpt-4","name":"GPT-4","provider":"OpenAI","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu":{"score":83.93,"unit":"%","sourceType":"paper","date":"","source":"http://arxiv.org/abs/2309.10305"},"c-eval":{"score":68.7,"unit":"%","sourceType":"official","date":"2023-05-15","source":"https://github.com/hkust-nlp/ceval#leaderboard"}}},{"id":"gpt-5-1-codex-mini","name":"GPT-5.1-Codex-mini","provider":"OpenAI","openWeights":false,"release":"2025-11-12","aliases":["gpt-5.1-codex-mini","GPT-5.1 Codex Mini","GPT-5.1-Codex-Mini"],"page":null,"best":{"lmarena-webdev":{"score":1244.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"terminal-bench":{"score":61.57,"unit":"%","sourceType":"official","date":"2025-11-12","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"}}},{"id":"gpt-5-2-chat-latest","name":"gpt-5.2-chat-latest","provider":"OpenAI","openWeights":false,"release":null,"aliases":["gpt-5.2-chat-latest-20260210"],"page":null,"best":{"lmarena-text":{"score":1475.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1278,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"gpt-5-3-codex","name":"GPT-5.3 Codex","provider":"OpenAI","openWeights":false,"release":"2026-02-05","aliases":["gpt-5.3-codex_high","GPT-5.3 Codex (high)","gpt-5.3-codex","GPT-5.3-Codex"],"page":null,"best":{"swe-bench-verified":{"score":74.79,"unit":"%","sourceType":"independent","date":"2026-02-25","source":"https://epoch.ai/benchmarks"},"terminal-bench":{"score":78.43,"unit":"%","sourceType":"official","date":"2026-02-05","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"}}},{"id":"gpt-5-4-pro","name":"GPT-5.4 Pro","provider":"OpenAI","openWeights":false,"release":"2026-03-05","aliases":["gpt-5.4-pro-2026-03-05_xhigh","GPT-5.4 Pro (xhigh)","gpt-5.4-pro-2026-03-05_unknown"],"page":null,"best":{"gpqa-diamond":{"score":94.6,"unit":"%","sourceType":"independent","date":"2026-03-20","source":"https://epoch.ai/benchmarks"},"hle":{"score":44.32,"unit":"%","sourceType":"compiled","date":"2026-03-05","source":"https://epoch.ai/benchmarks"}}},{"id":"gpt-5-5-pro","name":"GPT-5.5 Pro","provider":"OpenAI","openWeights":false,"release":"2026-04-23","aliases":["gpt-5.5-pro-pre-release_xhigh","GPT-5.5 Pro (xhigh)"],"page":null,"best":{"gpqa-diamond":{"score":93.92,"unit":"%","sourceType":"independent","date":"2026-04-24","source":"https://epoch.ai/benchmarks"},"aime":{"score":100,"unit":"%","sourceType":"independent","date":"2026-04-24","source":"https://epoch.ai/benchmarks"}}},{"id":"gpt-6-luna","name":"GPT-6 Luna","provider":"OpenAI","openWeights":false,"release":"2026-09-22","aliases":["gpt-6-luna_max","GPT-6 Luna (max)"],"page":null,"best":{"gpqa-diamond":{"score":90.47,"unit":"%","sourceType":"independent","date":"2026-09-22","source":"https://epoch.ai/benchmarks"},"aime":{"score":98.89,"unit":"%","sourceType":"independent","date":"2026-09-22","source":"https://epoch.ai/benchmarks"}}},{"id":"gpt-6-sol","name":"GPT-6 Sol","provider":"OpenAI","openWeights":false,"release":"2026-09-22","aliases":["gpt-6-sol_max","GPT-6 Sol (max)"],"page":null,"best":{"gpqa-diamond":{"score":94.32,"unit":"%","sourceType":"independent","date":"2026-09-22","source":"https://epoch.ai/benchmarks"},"aime":{"score":100,"unit":"%","sourceType":"independent","date":"2026-09-22","source":"https://epoch.ai/benchmarks"}}},{"id":"gpt-6-luna-max","name":"gpt-6-luna-max","provider":"OpenAI","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1442.6,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1580.9,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"}}},{"id":"gpt-6-sol-max","name":"gpt-6-sol-max","provider":"OpenAI","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1455.9,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1688.2,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"}}},{"id":"gpt-neo-2-7b","name":"GPT-Neo-2.7B","provider":"EleutherAI","openWeights":true,"release":null,"aliases":["EleutherAI/gpt-neo-2.7B"],"page":null,"best":{"open-llm-leaderboard":{"score":6.43,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"humaneval":{"score":6.7,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"gpt-neox-20b","name":"GPT-NeoX 20B","provider":"EleutherAI","openWeights":true,"release":null,"aliases":["EleutherAI/gpt-neox-20b"],"page":null,"best":{"open-llm-leaderboard":{"score":6.12,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu":{"score":33.6,"unit":"%","sourceType":"paper","date":"","source":"http://arxiv.org/abs/2302.13971"}}},{"id":"granite-3-0-2b-base","name":"Granite-3.0-2B-Base","provider":"IBM","openWeights":true,"release":null,"aliases":["ibm-granite/granite-3.0-2b-base"],"page":null,"best":{"open-llm-leaderboard":{"score":14.1,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu-pro":{"score":21.72,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"granite-3-0-2b-instruct","name":"granite-3.0-2b-instruct","provider":"IBM","openWeights":true,"release":null,"aliases":["ibm-granite/granite-3.0-2b-instruct"],"page":null,"best":{"lmarena-text":{"score":1156.6,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":18.4,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"granite-3-0-8b-base","name":"Granite-3.0-8B-Base","provider":"IBM","openWeights":true,"release":null,"aliases":["ibm-granite/granite-3.0-8b-base"],"page":null,"best":{"open-llm-leaderboard":{"score":21.69,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu-pro":{"score":31.03,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"granite-3-0-8b-instruct","name":"granite-3.0-8b-instruct","provider":"IBM","openWeights":true,"release":null,"aliases":["ibm-granite/granite-3.0-8b-instruct"],"page":null,"best":{"lmarena-text":{"score":1183.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":24.03,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"granite-3-1-1b-a400m-base","name":"Granite-3.1-1B-A400M-Base","provider":"IBM","openWeights":true,"release":null,"aliases":["ibm-granite/granite-3.1-1b-a400m-base"],"page":null,"best":{"open-llm-leaderboard":{"score":6.31,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu-pro":{"score":12.34,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"granite-3-1-1b-a400m-instruct","name":"Granite-3.1-1B-A400M-Instruct","provider":"IBM","openWeights":true,"release":null,"aliases":["ibm-granite/granite-3.1-1b-a400m-instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":10.13,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu-pro":{"score":13.27,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"granite-3-1-2b-base","name":"Granite-3.1-2B-Base","provider":"IBM","openWeights":true,"release":null,"aliases":["ibm-granite/granite-3.1-2b-base"],"page":null,"best":{"open-llm-leaderboard":{"score":13.2,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu-pro":{"score":23.89,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"granite-3-1-3b-a800m-base","name":"Granite-3.1-3B-A800M-Base","provider":"IBM","openWeights":true,"release":null,"aliases":["ibm-granite/granite-3.1-3b-a800m-base"],"page":null,"best":{"open-llm-leaderboard":{"score":10,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu-pro":{"score":20.39,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"granite-3-1-3b-a800m-instruct","name":"Granite-3.1-3B-A800M-Instruct","provider":"IBM","openWeights":true,"release":null,"aliases":["ibm-granite/granite-3.1-3b-a800m-instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":17.28,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu-pro":{"score":25.42,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"granite-3-1-8b-base","name":"Granite-3.1-8B-Base","provider":"IBM","openWeights":true,"release":null,"aliases":["ibm-granite/granite-3.1-8b-base"],"page":null,"best":{"open-llm-leaderboard":{"score":20.06,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu-pro":{"score":33.08,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"granite-3-2-8b-instruct","name":"Granite-3.2-8B-Instruct","provider":"IBM","openWeights":true,"release":null,"aliases":["Granite-3.2-8B-Instruct (FC)","ibm-granite/granite-3.2-8b-instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":30.77,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"bfcl":{"score":26.87,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"granite-4-0-1b","name":"granite-4.0-1b","provider":"IBM","openWeights":null,"release":"2025-10-28","aliases":[],"page":null,"best":{"gpqa-diamond":{"score":23.99,"unit":"%","sourceType":"independent","date":"2026-08-28","source":"https://epoch.ai/benchmarks"},"aime":{"score":0.83,"unit":"%","sourceType":"independent","date":"2026-08-30","source":"https://epoch.ai/benchmarks"}}},{"id":"granite-4-0-micro","name":"granite-4.0-micro","provider":"IBM","openWeights":null,"release":"2025-10-02","aliases":[],"page":null,"best":{"gpqa-diamond":{"score":28.28,"unit":"%","sourceType":"independent","date":"2026-08-30","source":"https://epoch.ai/benchmarks"},"aime":{"score":2.78,"unit":"%","sourceType":"independent","date":"2026-08-30","source":"https://epoch.ai/benchmarks"}}},{"id":"granite-4-1-8b","name":"granite-4.1-8b","provider":"IBM","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1304,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1191.6,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"}}},{"id":"grok-2","name":"Grok-2","provider":"xAI","openWeights":false,"release":null,"aliases":["grok-2-2024-08-13"],"page":null,"best":{"lmarena-text":{"score":1335.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"mmlu-pro":{"score":75.46,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"grok-2-mini","name":"Grok-2-mini","provider":"xAI","openWeights":false,"release":null,"aliases":["grok-2-mini-2024-08-13"],"page":null,"best":{"lmarena-text":{"score":1308.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"mmlu-pro":{"score":71.85,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"grok-4-1","name":"grok-4.1-thinking","provider":"xAI","openWeights":false,"release":"2025-11-17","aliases":["grok-4.1"],"page":null,"best":{"lmarena-text":{"score":1465.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1214.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"}}},{"id":"grok-4-20-multi-agent-beta-0309","name":"grok-4.20-multi-agent-beta-0309","provider":"xAI","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1470.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1250.3,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"grok-code-fast-1","name":"grok-code-fast-1","provider":"xAI","openWeights":false,"release":"2025-08-28","aliases":["Grok Code Fast 1"],"page":null,"best":{"lmarena-webdev":{"score":1167.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"terminal-bench":{"score":25.84,"unit":"%","sourceType":"official","date":"2025-08-28","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"}}},{"id":"hunyuan-hy3-preview","name":"hunyuan-hy3-preview","provider":"Tencent","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1408.9,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1355.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"}}},{"id":"hunyuan-large","name":"Hunyuan-Large","provider":"Tencent","openWeights":false,"release":null,"aliases":["hunyuan-large-2025-02-10"],"page":null,"best":{"lmarena-text":{"score":1326.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"mmlu-pro":{"score":60.2,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"hunyuan-large-vision","name":"hunyuan-large-vision","provider":"Tencent","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1293.9,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1148.8,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"hunyuan-t1","name":"Hunyuan-T1","provider":"Tencent","openWeights":false,"release":null,"aliases":["hunyuan-t1-20250711"],"page":null,"best":{"lmarena-text":{"score":1387.2,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"mmlu-pro":{"score":87.2,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"hunyuan-vision-1-5","name":"hunyuan-vision-1.5-thinking","provider":"Tencent","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1393.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1155.6,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"hy3","name":"hy3","provider":"Tencent","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1454.2,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1508.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"}}},{"id":"internlm2-5-20b-chat","name":"internlm2_5-20b-chat","provider":"Shanghai AI Lab (InternLM)","openWeights":true,"release":null,"aliases":["internlm/internlm2_5-20b-chat"],"page":null,"best":{"lmarena-text":{"score":1190.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":38.88,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"jamba-1-5-mini","name":"Jamba 1.5 Mini","provider":"AI21 Labs","openWeights":true,"release":null,"aliases":["jamba-1.5-mini"],"page":null,"best":{"lmarena-text":{"score":1239.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"mmlu":{"score":69.9,"unit":"%","sourceType":"official","date":"","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"}}},{"id":"kimi-k3-max","name":"kimi-k3-max","provider":"Moonshot AI","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1488.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1654.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"}}},{"id":"llama-13b","name":"LLaMA-13B","provider":"Meta","openWeights":true,"release":"2023-02-24","aliases":["llama-13b","LLAMA 1 13B","LLaMA 13B"],"page":null,"best":{"lmarena-text":{"score":975,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"mmlu":{"score":46.9,"unit":"%","sourceType":"paper","date":"2023-02-24","source":"http://arxiv.org/abs/2307.09288"}}},{"id":"llama-3-70b-instruct","name":"Llama-3-70B-Instruct","provider":"Meta","openWeights":true,"release":null,"aliases":["llama-3-70b-instruct"],"page":null,"best":{"lmarena-text":{"score":1276.6,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"mmlu-pro":{"score":56.2,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"llama-3-8b-instruct","name":"Llama-3-8B-Instruct","provider":"Meta","openWeights":true,"release":null,"aliases":["llama-3-8b-instruct"],"page":null,"best":{"lmarena-text":{"score":1223.6,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"mmlu-pro":{"score":40.98,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"llama-3-1-nemotron-70b-instruct-hf","name":"Llama-3.1-Nemotron-70B-Instruct-HF","provider":"NVIDIA","openWeights":true,"release":null,"aliases":["nvidia/Llama-3.1-Nemotron-70B-Instruct-HF"],"page":null,"best":{"open-llm-leaderboard":{"score":36.91,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu-pro":{"score":62.78,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"llama-3-1-nemotron-ultra-253b-v1","name":"Llama-3.1-Nemotron-Ultra-253B-v1","provider":"NVIDIA","openWeights":true,"release":null,"aliases":["llama-3.1-nemotron-ultra-253b-v1","Llama-3.1-Nemotron-Ultra-253B-v1 (FC)"],"page":null,"best":{"lmarena-text":{"score":1347.6,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"bfcl":{"score":10,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"llama-3-1-tulu-3-70b","name":"llama-3.1-tulu-3-70b","provider":"Ai2","openWeights":true,"release":null,"aliases":["allenai/Llama-3.1-Tulu-3-70B"],"page":null,"best":{"lmarena-text":{"score":1286.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":42.33,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"llama-3-1-tulu-3-8b","name":"llama-3.1-tulu-3-8b","provider":"Ai2","openWeights":true,"release":null,"aliases":["allenai/Llama-3.1-Tulu-3-8B"],"page":null,"best":{"lmarena-text":{"score":1220.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":26.26,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"llama-65b","name":"LLaMA-65B","provider":"Meta","openWeights":true,"release":"2023-02-24","aliases":["LLAMA 1 65B","LLaMA 65B"],"page":null,"best":{"mmlu":{"score":63.4,"unit":"%","sourceType":"paper","date":"2023-02-24","source":"http://arxiv.org/abs/2307.09288"},"c-eval":{"score":38.8,"unit":"%","sourceType":"official","date":"2023-05-15","source":"https://github.com/hkust-nlp/ceval#leaderboard"}}},{"id":"longcat-flash-chat","name":"LongCat-Flash-Chat","provider":"Meituan","openWeights":true,"release":null,"aliases":["longcat-flash-chat"],"page":null,"best":{"lmarena-text":{"score":1401,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"mmlu-pro":{"score":82.7,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"magistral-small-1-0","name":"Magistral Small 1.0","provider":"Mistral AI","openWeights":true,"release":"2025-06-10","aliases":["magistral-small-2506"],"page":null,"best":{"gpqa-diamond":{"score":56.06,"unit":"%","sourceType":"independent","date":"2026-08-06","source":"https://epoch.ai/benchmarks"},"aime":{"score":30,"unit":"%","sourceType":"independent","date":"2026-08-06","source":"https://epoch.ai/benchmarks"}}},{"id":"magistral-small-1-2","name":"Magistral Small 1.2","provider":"Mistral AI","openWeights":true,"release":"2025-09-18","aliases":["magistral-small-2509"],"page":null,"best":{"gpqa-diamond":{"score":47.6,"unit":"%","sourceType":"independent","date":"2026-08-30","source":"https://epoch.ai/benchmarks"},"aime":{"score":28.06,"unit":"%","sourceType":"independent","date":"2026-08-30","source":"https://epoch.ai/benchmarks"}}},{"id":"mercury-2","name":"Mercury 2","provider":"Inception Labs","openWeights":false,"release":"2026-02-20","aliases":["mercury-2"],"page":null,"best":{"lmarena-text":{"score":1343.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1170.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"}}},{"id":"mimo-v2-flash","name":"mimo-v2-flash (non-thinking)","provider":"Xiaomi Corp","openWeights":true,"release":"2025-12-16","aliases":["mimo-v2-flash (thinking)"],"page":null,"best":{"lmarena-text":{"score":1391.6,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1330.2,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"}}},{"id":"mimo-v2-omni","name":"mimo-v2-omni","provider":"Xiaomi","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1430.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1216.1,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"mimo-v2-pro","name":"MiMo-V2-Pro","provider":"Xiaomi Corp","openWeights":false,"release":"2026-03-18","aliases":["mimo-v2-pro"],"page":null,"best":{"lmarena-text":{"score":1447.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1433.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"}}},{"id":"mimo-v2-5-pro","name":"MiMo-V2.5-Pro","provider":"Xiaomi Corp","openWeights":true,"release":"2026-04-23","aliases":["mimo-v2.5-pro"],"page":null,"best":{"lmarena-text":{"score":1467.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1479.2,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"}}},{"id":"minimax-m1","name":"MiniMax-M1","provider":"MiniMax","openWeights":true,"release":null,"aliases":["minimax-m1"],"page":null,"best":{"lmarena-text":{"score":1363.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"mmlu-pro":{"score":81.1,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"minimax-m2-1","name":"MiniMax-M2.1","provider":"MiniMax","openWeights":true,"release":"2025-12-23","aliases":["MiniMax M2.1"],"page":null,"best":{"mmlu-pro":{"score":88,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"terminal-bench":{"score":36.63,"unit":"%","sourceType":"official","date":"2025-12-23","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"}}},{"id":"minimax-m2-1-preview","name":"minimax-m2.1-preview","provider":"MiniMax","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1384.6,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1384.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"}}},{"id":"ministral-3b","name":"Ministral 3B","provider":"Mistral AI","openWeights":false,"release":"2024-10-16","aliases":["ministral-3b-2410"],"page":null,"best":{"gpqa-diamond":{"score":25.25,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"},"math-level-5":{"score":14.44,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"}}},{"id":"mistral-medium-3-1","name":"Mistral Medium 3.1","provider":"Mistral AI","openWeights":false,"release":"2025-08-12","aliases":["mistral-medium-2508"],"page":null,"best":{"lmarena-text":{"score":1407.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1159.4,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"mistral-small-3-1-24b-instruct-2503","name":"mistral-small-3.1-24b-instruct-2503","provider":"Mistral AI","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1302.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1127.1,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"mistral-small-instruct-2409","name":"Mistral-Small-Instruct-2409","provider":"Mistral AI","openWeights":true,"release":null,"aliases":["mistralai/Mistral-Small-Instruct-2409"],"page":null,"best":{"open-llm-leaderboard":{"score":29.92,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu-pro":{"score":48.4,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"molmo-2-8b","name":"molmo-2-8b","provider":"Ai2","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1322,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1111.7,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"mpt-7b","name":"MPT-7B","provider":"MosaicML","openWeights":true,"release":"2023-05-05","aliases":["mpt-7b","MPT 7B","mosaicml/mpt-7b"],"page":null,"best":{"open-llm-leaderboard":{"score":6.03,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu":{"score":30.8,"unit":"%","sourceType":"paper","date":"2023-05-05","source":"https://arxiv.org/pdf/2309.16609"}}},{"id":"muse-spark-1-3","name":"Muse Spark 1.3","provider":"Meta","openWeights":false,"release":"2026-09-02","aliases":["muse-spark-1.3 (xHigh)","muse-spark-1.3_xhigh","Muse Spark 1.3 (xhigh)"],"page":null,"best":{"lmarena-webdev":{"score":1625.9,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"},"aime":{"score":99.17,"unit":"%","sourceType":"independent","date":"2026-09-17","source":"https://epoch.ai/benchmarks"}}},{"id":"muse-spark-open","name":"Muse Spark Open","provider":"Meta","openWeights":true,"release":"2026-10-15","aliases":["Muse-Spark-Open-816B-A42B_xhigh","Muse Spark Open (xhigh)"],"page":null,"best":{"gpqa-diamond":{"score":88.57,"unit":"%","sourceType":"independent","date":"2026-10-15","source":"https://epoch.ai/benchmarks"},"aime":{"score":98.06,"unit":"%","sourceType":"independent","date":"2026-10-15","source":"https://epoch.ai/benchmarks"}}},{"id":"muse-glimmer","name":"muse-glimmer","provider":"Meta","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1424.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1355,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"}}},{"id":"nemotron-3-ultra","name":"Nemotron 3 Ultra","provider":"NVIDIA","openWeights":true,"release":"2026-06-04","aliases":["nemotron-3-ultra"],"page":null,"best":{"gpqa-diamond":{"score":85.35,"unit":"%","sourceType":"independent","date":"2026-08-10","source":"https://epoch.ai/benchmarks"},"aime":{"score":86.67,"unit":"%","sourceType":"independent","date":"2026-08-10","source":"https://epoch.ai/benchmarks"}}},{"id":"nous-hermes-2-mixtral-8x7b-dpo","name":"nous-hermes-2-mixtral-8x7b-dpo","provider":"NousResearch","openWeights":true,"release":null,"aliases":["NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO"],"page":null,"best":{"lmarena-text":{"score":1164.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":27.35,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"openhermes-2-5-mistral-7b","name":"openhermes-2.5-mistral-7b","provider":"teknium","openWeights":true,"release":null,"aliases":["teknium/OpenHermes-2.5-Mistral-7B"],"page":null,"best":{"lmarena-text":{"score":1175.9,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":21.32,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"palmyra-x-004","name":"Palmyra-X-004","provider":"Writer","openWeights":false,"release":null,"aliases":["palmyra-x-004 (FC)"],"page":null,"best":{"mmlu":{"score":73.9,"unit":"%","sourceType":"official","date":"","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"bfcl":{"score":27.87,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"phi-1-5","name":"Phi-1.5","provider":"Microsoft","openWeights":true,"release":"2023-09-11","aliases":["phi-1_5","phi-1.5","microsoft/phi-1_5"],"page":null,"best":{"open-llm-leaderboard":{"score":7.17,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu":{"score":37.6,"unit":"%","sourceType":"paper","date":"2023-09-11","source":"http://arxiv.org/abs/2309.05463"}}},{"id":"phi-2","name":"Phi-2","provider":"Microsoft","openWeights":true,"release":"2023-12-12","aliases":["phi-2","microsoft/phi-2"],"page":null,"best":{"open-llm-leaderboard":{"score":15.53,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu":{"score":58.4,"unit":"%","sourceType":"official","date":"2023-12-12","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"}}},{"id":"phi-3-medium-4k-instruct","name":"phi-3-medium-4k-instruct","provider":"Microsoft","openWeights":true,"release":null,"aliases":["microsoft/Phi-3-medium-4k-instruct"],"page":null,"best":{"lmarena-text":{"score":1197.9,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":33.1,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"phi-3-5-mini","name":"Phi-3.5-mini","provider":"Microsoft","openWeights":true,"release":"2024-08-16","aliases":["Phi-3.5-mini-instruct","microsoft/Phi-3.5-mini-instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":28.18,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu-pro":{"score":47.87,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"phi-4-mini","name":"Phi-4-mini","provider":"Microsoft","openWeights":true,"release":null,"aliases":["microsoft/Phi-4-mini-instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":29.41,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu-pro":{"score":52.8,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"qwen-3-5-plus-hosted-397b-a17b","name":"Qwen 3.5 Plus (hosted 397B-A17B)","provider":"Alibaba (Qwen)","openWeights":null,"release":"2026-02-16","aliases":["qwen3.5-plus","Qwen3.5 Plus"],"page":null,"best":{"gpqa-diamond":{"score":84.85,"unit":"%","sourceType":"independent","date":"2026-08-07","source":"https://epoch.ai/benchmarks"},"aime":{"score":86.67,"unit":"%","sourceType":"independent","date":"2026-08-07","source":"https://epoch.ai/benchmarks"}}},{"id":"qwen-3-6-flash","name":"Qwen 3.6 Flash","provider":"Alibaba (Qwen)","openWeights":null,"release":"2026-04-27","aliases":["qwen3.6-flash","Qwen 3.6 Flash (2026-04-16)"],"page":null,"best":{"gpqa-diamond":{"score":83.33,"unit":"%","sourceType":"independent","date":"2026-08-07","source":"https://epoch.ai/benchmarks"},"aime":{"score":84.44,"unit":"%","sourceType":"independent","date":"2026-08-07","source":"https://epoch.ai/benchmarks"}}},{"id":"qwen-14b","name":"Qwen-14B","provider":"Alibaba (Qwen)","openWeights":true,"release":"2023-09-24","aliases":["qwen-14b-chat","QWEN 14B","Qwen 14B","Qwen-14B-Chat","Qwen-Chat 14B"],"page":null,"best":{"lmarena-text":{"score":1139.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"mmlu":{"score":66.3,"unit":"%","sourceType":"paper","date":"2023-09-28","source":"http://arxiv.org/abs/2402.16819"}}},{"id":"qwen1-5-4b-chat","name":"qwen1.5-4b-chat","provider":"Alibaba (Qwen)","openWeights":true,"release":null,"aliases":["Qwen/Qwen1.5-4B-Chat"],"page":null,"best":{"lmarena-text":{"score":1091.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":12.63,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"qwen2-0-5b","name":"Qwen2-0.5B","provider":"Alibaba (Qwen)","openWeights":true,"release":null,"aliases":["Qwen/Qwen2-0.5B"],"page":null,"best":{"open-llm-leaderboard":{"score":7.22,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu-pro":{"score":14.97,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"qwen2-0-5b-instruct","name":"Qwen2-0.5B-Instruct","provider":"Alibaba (Qwen)","openWeights":true,"release":null,"aliases":["Qwen/Qwen2-0.5B-Instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":6.59,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu-pro":{"score":15.93,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"qwen2-1-5b","name":"Qwen2-1.5B","provider":"Alibaba (Qwen)","openWeights":true,"release":null,"aliases":["Qwen/Qwen2-1.5B"],"page":null,"best":{"open-llm-leaderboard":{"score":10.45,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu-pro":{"score":22.56,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"qwen2-1-5b-instruct","name":"Qwen2-1.5B-Instruct","provider":"Alibaba (Qwen)","openWeights":true,"release":null,"aliases":["Qwen/Qwen2-1.5B-Instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":14.14,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu-pro":{"score":22.62,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"qwen2-7b","name":"Qwen2-7B-Instruct","provider":"Alibaba (Qwen)","openWeights":true,"release":null,"aliases":["Qwen2-7B","Qwen/Qwen2-7B-Instruct","Qwen/Qwen2-7B"],"page":null,"best":{"open-llm-leaderboard":{"score":27.94,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu-pro":{"score":47.24,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"qwen2-vl-7b-instruct","name":"qwen2-vl-7b-instruct","provider":"Alibaba (Qwen)","openWeights":true,"release":null,"aliases":["Qwen/Qwen2-VL-7B-Instruct"],"page":null,"best":{"lmarena-vision":{"score":1030.8,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"},"open-llm-leaderboard":{"score":26.49,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"qwen2-5-0-5b","name":"Qwen2.5-0.5B","provider":"Alibaba (Qwen)","openWeights":true,"release":null,"aliases":["Qwen/Qwen2.5-0.5B"],"page":null,"best":{"open-llm-leaderboard":{"score":6.55,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu-pro":{"score":14.92,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"qwen2-5-1-5b","name":"Qwen2.5-1.5B","provider":"Alibaba (Qwen)","openWeights":true,"release":null,"aliases":["Qwen/Qwen2.5-1.5B-Instruct","Qwen/Qwen2.5-1.5B"],"page":null,"best":{"open-llm-leaderboard":{"score":18.43,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu-pro":{"score":32.1,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"qwen2-5-3b","name":"Qwen2.5-3B","provider":"Alibaba (Qwen)","openWeights":true,"release":null,"aliases":["Qwen/Qwen2.5-3B-Instruct","Qwen/Qwen2.5-3B"],"page":null,"best":{"open-llm-leaderboard":{"score":27.16,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu-pro":{"score":43.73,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"qwen2-5-coder-7b","name":"Qwen2.5-Coder (7B)","provider":"Alibaba (Qwen)","openWeights":true,"release":"2024-09-18","aliases":["Qwen2.5-Coder-7B","Qwen/Qwen2.5-Coder-7B-Instruct","Qwen/Qwen2.5-Coder-7B"],"page":null,"best":{"open-llm-leaderboard":{"score":28.05,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu":{"score":68,"unit":"%","sourceType":"paper","date":"2024-09-18","source":"http://arxiv.org/abs/2409.12186"}}},{"id":"qwen2-5-coder-14b","name":"Qwen2.5-Coder-14B","provider":"Alibaba (Qwen)","openWeights":true,"release":"2024-09-18","aliases":["Qwen/Qwen2.5-Coder-14B"],"page":null,"best":{"open-llm-leaderboard":{"score":24.83,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu":{"score":75.2,"unit":"%","sourceType":"paper","date":"2024-09-18","source":"http://arxiv.org/abs/2409.12186"}}},{"id":"qwen2-5-coder-32b","name":"Qwen2.5-Coder-32B","provider":"Alibaba (Qwen)","openWeights":true,"release":"2024-09-18","aliases":["Qwen2.5-Coder-3B","Qwen/Qwen2.5-Coder-32B"],"page":null,"best":{"open-llm-leaderboard":{"score":33.26,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu":{"score":61.2,"unit":"%","sourceType":"paper","date":"2024-09-18","source":"http://arxiv.org/abs/2409.12186"}}},{"id":"qwen3-vl-235b-a22b-instruct","name":"qwen3-vl-235b-a22b-instruct","provider":"Alibaba (Qwen)","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1413.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1215.1,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"qwen3-vl-235b-a22b","name":"qwen3-vl-235b-a22b-thinking","provider":"Alibaba (Qwen)","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1394.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1188,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"qwen3-5-4b","name":"Qwen3.5-4B","provider":"Alibaba (Qwen)","openWeights":true,"release":"2026-02-24","aliases":["qwen3.5-4b_none"],"page":null,"best":{"mmlu-pro":{"score":79.1,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"},"aime":{"score":55.83,"unit":"%","sourceType":"independent","date":"2026-08-28","source":"https://epoch.ai/benchmarks"}}},{"id":"qwen3-6-27b","name":"Qwen3.6 27B","provider":"Alibaba (Qwen)","openWeights":true,"release":"2026-04-22","aliases":["qwen3.6-27b","qwen3.6-27b_none"],"page":null,"best":{"gpqa-diamond":{"score":85.86,"unit":"%","sourceType":"independent","date":"2026-08-07","source":"https://epoch.ai/benchmarks"},"aime":{"score":91.11,"unit":"%","sourceType":"independent","date":"2026-08-07","source":"https://epoch.ai/benchmarks"}}},{"id":"qwen3-7-flash","name":"Qwen3.7 Flash","provider":"Alibaba (Qwen)","openWeights":false,"release":"2026-07-27","aliases":["qwen3.7-flash","qwen3.7-flash_none"],"page":null,"best":{"gpqa-diamond":{"score":82.32,"unit":"%","sourceType":"independent","date":"2026-08-07","source":"https://epoch.ai/benchmarks"},"aime":{"score":86.67,"unit":"%","sourceType":"independent","date":"2026-08-07","source":"https://epoch.ai/benchmarks"}}},{"id":"smollm-1-7b","name":"SmolLM-1.7B","provider":"Hugging Face","openWeights":true,"release":null,"aliases":["HuggingFaceTB/SmolLM-1.7B"],"page":null,"best":{"open-llm-leaderboard":{"score":5.58,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu-pro":{"score":11.93,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"smollm-135m","name":"SmolLM-135M","provider":"Hugging Face","openWeights":true,"release":null,"aliases":["HuggingFaceTB/SmolLM-135M"],"page":null,"best":{"open-llm-leaderboard":{"score":6.95,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu-pro":{"score":11.22,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"smollm-360m","name":"SmolLM-360M","provider":"Hugging Face","openWeights":true,"release":null,"aliases":["HuggingFaceTB/SmolLM-360M"],"page":null,"best":{"open-llm-leaderboard":{"score":6.26,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu-pro":{"score":10.95,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"smollm2-1-7b","name":"SmolLM2-1.7B","provider":"Hugging Face","openWeights":true,"release":null,"aliases":["HuggingFaceTB/SmolLM2-1.7B"],"page":null,"best":{"open-llm-leaderboard":{"score":9.58,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu-pro":{"score":18.31,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"smollm2-1-7b-instruct","name":"smollm2-1.7b-instruct","provider":"Hugging Face","openWeights":true,"release":null,"aliases":["HuggingFaceTB/SmolLM2-1.7B-Instruct"],"page":null,"best":{"lmarena-text":{"score":1114.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"open-llm-leaderboard":{"score":15.02,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"smollm2-135m","name":"SmolLM2-135M","provider":"Hugging Face","openWeights":true,"release":null,"aliases":["HuggingFaceTB/SmolLM2-135M"],"page":null,"best":{"open-llm-leaderboard":{"score":5.7,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu-pro":{"score":10.85,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"smollm2-360m","name":"SmolLM2-360M","provider":"Hugging Face","openWeights":true,"release":null,"aliases":["HuggingFaceTB/SmolLM2-360M"],"page":null,"best":{"open-llm-leaderboard":{"score":6.25,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu-pro":{"score":11.38,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"solar-pro4","name":"solar-pro4","provider":"upstage","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1386.2,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1371,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"}}},{"id":"stable-beluga-2","name":"Stable Beluga 2","provider":"Stability AI","openWeights":true,"release":"2023-07-20","aliases":["StableBeluga2","StableBeluga2 70B","stabilityai/StableBeluga2"],"page":null,"best":{"open-llm-leaderboard":{"score":22.81,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu":{"score":68.6,"unit":"%","sourceType":"paper","date":"2023-07-20","source":"https://arxiv.org/pdf/2309.16609"}}},{"id":"starcoder-2-15b","name":"StarCoder 2 15B","provider":"Hugging Face","openWeights":true,"release":"2024-02-20","aliases":["starcoder2-15b","StarCoder2-15B"],"page":null,"best":{"mmlu":{"score":64.1,"unit":"%","sourceType":"paper","date":"2024-02-20","source":"http://arxiv.org/abs/2409.12186"},"humaneval":{"score":37.8,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"starcoder-2-3b","name":"StarCoder 2 3B","provider":"Hugging Face","openWeights":true,"release":"2024-02-22","aliases":["starcoder2-3b","StarCoder2-3B"],"page":null,"best":{"mmlu":{"score":36.6,"unit":"%","sourceType":"paper","date":"2024-02-22","source":"http://arxiv.org/abs/2409.12186"},"humaneval":{"score":27.4,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"starcoder-2-7b","name":"StarCoder 2 7B","provider":"Hugging Face","openWeights":true,"release":"2024-02-20","aliases":["starcoder2-7b","StarCoder2-7B"],"page":null,"best":{"mmlu":{"score":38.8,"unit":"%","sourceType":"paper","date":"2024-02-20","source":"http://arxiv.org/abs/2409.12186"},"humaneval":{"score":29.9,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"step-1o-turbo-202506","name":"step-1o-turbo-202506","provider":"StepFun","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1319.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1155.8,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"step-3","name":"step-3","provider":"StepFun","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1349.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-vision":{"score":1144.9,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"trinity-large","name":"Trinity Large Thinking","provider":"Arcee AI","openWeights":true,"release":"2026-04-01","aliases":["trinity-large-thinking"],"page":null,"best":{"lmarena-text":{"score":1367.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"lmarena-webdev":{"score":1238.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"}}},{"id":"vicuna-7b","name":"vicuna-7b","provider":"LMSYS","openWeights":true,"release":null,"aliases":["Vicuna-7B"],"page":null,"best":{"lmarena-text":{"score":1115.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"humaneval":{"score":11.6,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"yi-1-5-6b-chat","name":"Yi-1.5-6B-Chat","provider":"01.AI","openWeights":true,"release":null,"aliases":["01-ai/Yi-1.5-6B-Chat"],"page":null,"best":{"open-llm-leaderboard":{"score":22.78,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu-pro":{"score":38.23,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"yi-1-5-9b-chat","name":"Yi-1.5-9B-Chat","provider":"01.AI","openWeights":true,"release":null,"aliases":["01-ai/Yi-1.5-9B-Chat","01-ai/Yi-1.5-9B-Chat-16K"],"page":null,"best":{"open-llm-leaderboard":{"score":29.53,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu-pro":{"score":45.95,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"yi-9b","name":"Yi-9B","provider":"01.AI","openWeights":true,"release":"2024-03-01","aliases":["01-ai/Yi-9B","01-ai/Yi-9B-200K"],"page":null,"best":{"open-llm-leaderboard":{"score":17.81,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"},"mmlu":{"score":68.4,"unit":"%","sourceType":"paper","date":"2024-03-01","source":"http://arxiv.org/abs/2403.04652"}}},{"id":"yi-large","name":"Yi-Large","provider":"01.AI","openWeights":false,"release":"2024-05-13","aliases":["Yi-large","Yi Large (Preview)"],"page":null,"best":{"mmlu":{"score":79.3,"unit":"%","sourceType":"official","date":"2024-05-13","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},"mmlu-pro":{"score":58.09,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"yi-lightning","name":"Yi-Lightning","provider":"01.AI","openWeights":false,"release":"2024-12-02","aliases":["yi-lightning"],"page":null,"best":{"lmarena-text":{"score":1328.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"mmlu-pro":{"score":62.38,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"zephyr-7b-beta","name":"Zephyr-7B-Beta","provider":"Hugging Face","openWeights":true,"release":null,"aliases":["zephyr-7b-beta"],"page":null,"best":{"lmarena-text":{"score":1130.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"},"mmlu-pro":{"score":32.97,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"https-huggingface-co-agentica-org-deepswe-preview","name":"/huggingface.co/agentica-org/DeepSWE-Preview","provider":"OpenAI","openWeights":null,"release":null,"aliases":["https://huggingface.co/agentica-org/DeepSWE-Preview","TTS(Bo16)","DeepSWE-Preview + TTS(Bo16)","DeepSWE-Preview"],"page":null,"best":{"swe-bench-verified":{"score":58.8,"unit":"%","sourceType":"official","date":"2025-06-29","source":"https://www.swebench.com/#verified"}}},{"id":"https-huggingface-co-qwen-qwen3-coder-30b-a3b-instruct","name":"/huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct","provider":"Alibaba (Qwen)","openWeights":null,"release":null,"aliases":["https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct","Qwen3-Coder-30B-A3B-Instruct","OpenHands + Qwen3-Coder-30B-A3B-Instruct"],"page":null,"best":{"swe-bench-verified":{"score":51.6,"unit":"%","sourceType":"official","date":"2025-08-05","source":"https://www.swebench.com/#verified"}}},{"id":"gemini-3-flash-12-25","name":"25)","provider":"Google","openWeights":null,"release":null,"aliases":["Gemini-3-Flash(12/25)"],"page":null,"best":{"mmlu-pro":{"score":88.6,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"aceinstruct-1-5b","name":"AceInstruct-1.5B","provider":"NVIDIA","openWeights":true,"release":null,"aliases":["nvidia/AceInstruct-1.5B"],"page":null,"best":{"open-llm-leaderboard":{"score":18.12,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"aceinstruct-72b","name":"AceInstruct-72B","provider":"NVIDIA","openWeights":true,"release":null,"aliases":["nvidia/AceInstruct-72B"],"page":null,"best":{"open-llm-leaderboard":{"score":40.41,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"aceinstruct-7b","name":"AceInstruct-7B","provider":"NVIDIA","openWeights":true,"release":null,"aliases":["nvidia/AceInstruct-7B"],"page":null,"best":{"open-llm-leaderboard":{"score":33.06,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"acemath-1-5b-instruct","name":"AceMath-1.5B-Instruct","provider":"NVIDIA","openWeights":true,"release":null,"aliases":["nvidia/AceMath-1.5B-Instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":20.19,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"acemath-72b-instruct","name":"AceMath-72B-Instruct","provider":"NVIDIA","openWeights":true,"release":null,"aliases":["nvidia/AceMath-72B-Instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":36.66,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"acemath-72b-rm","name":"AceMath-72B-RM","provider":"NVIDIA","openWeights":true,"release":null,"aliases":["nvidia/AceMath-72B-RM"],"page":null,"best":{"open-llm-leaderboard":{"score":3.43,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"acemath-7b-instruct","name":"AceMath-7B-Instruct","provider":"NVIDIA","openWeights":true,"release":null,"aliases":["nvidia/AceMath-7B-Instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":30.33,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"acemath-7b-rm","name":"AceMath-7B-RM","provider":"NVIDIA","openWeights":true,"release":null,"aliases":["nvidia/AceMath-7B-RM"],"page":null,"best":{"open-llm-leaderboard":{"score":3.22,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"alpaca-13b","name":"alpaca-13b","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1070.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"amazon-nova-2-lite-v1-0","name":"Amazon-Nova-2-Lite-v1:0","provider":"Amazon","openWeights":false,"release":null,"aliases":["Amazon-Nova-2-Lite-v1:0 (FC)"],"page":null,"best":{"bfcl":{"score":27.1,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"amazon-nova-experimental-chat-10-09","name":"amazon-nova-experimental-chat-10-09","provider":"Amazon","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1346.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"amazon-nova-experimental-chat-10-20","name":"amazon-nova-experimental-chat-10-20","provider":"Amazon","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1348,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"amazon-nova-experimental-chat-11-10","name":"amazon-nova-experimental-chat-11-10","provider":"Amazon","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1364,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"amazon-nova-experimental-chat-12-10","name":"amazon-nova-experimental-chat-12-10","provider":"Amazon","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1393.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"amazon-nova-experimental-chat-26-01-10","name":"amazon-nova-experimental-chat-26-01-10","provider":"Amazon","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1412.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"amazon-nova-experimental-chat-26-02-10","name":"amazon-nova-experimental-chat-26-02-10","provider":"Amazon","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1426.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"amazon-nova-premier-v1-0","name":"amazon.nova-premier-v1:0","provider":"Amazon","openWeights":null,"release":null,"aliases":["Amazon.nova Premier v1:0","Amazon Nova Premier 1.0 (2025-04-30)"],"page":null,"best":{"swe-bench-verified":{"score":42.4,"unit":"%","sourceType":"official","date":"2025-05-27","source":"https://www.swebench.com/#verified"}}},{"id":"aquilachat2-34b","name":"AquilaChat2 34B","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu":{"score":66.7,"unit":"%","sourceType":"paper","date":"","source":"http://arxiv.org/abs/2403.04652"}}},{"id":"arch-agent-1-5b","name":"Arch-Agent-1.5B","provider":"katanemo","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"bfcl":{"score":32.14,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"arch-agent-32b","name":"Arch-Agent-32B","provider":"katanemo","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"bfcl":{"score":45.37,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"arch-agent-3b","name":"Arch-Agent-3B","provider":"katanemo","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"bfcl":{"score":35.36,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"arctic-instruct","name":"Arctic Instruct","provider":"Snowflake","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu":{"score":67.7,"unit":"%","sourceType":"official","date":"","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"}}},{"id":"artigenz-coder-ds-6-7b","name":"Artigenz-Coder-DS-6.7B","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":72.6,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"athene-70b-0725","name":"athene-70b-0725","provider":"Nexusflow","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1306.6,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"athene-v2-chat-0-shot","name":"Athene-V2-Chat (0-shot)","provider":"Nexusflow","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":73.11,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"aya-23-35b","name":"aya-23-35B","provider":"Cohere","openWeights":true,"release":null,"aliases":["CohereForAI/aya-23-35B"],"page":null,"best":{"open-llm-leaderboard":{"score":24.76,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"aya-23-8b","name":"aya-23-8B","provider":"Cohere","openWeights":true,"release":null,"aliases":["CohereForAI/aya-23-8B"],"page":null,"best":{"open-llm-leaderboard":{"score":16.01,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"azerogpt","name":"azerogpt","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":63.07,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"baichuan-1-13b","name":"Baichuan 1-13B","provider":"Baichuan","openWeights":true,"release":"2023-07-11","aliases":["Baichuan-13B-Base","Baichuan 1-13B-Base"],"page":null,"best":{"mmlu":{"score":51.6,"unit":"%","sourceType":"paper","date":"2023-07-11","source":"http://arxiv.org/abs/2309.10305"}}},{"id":"baichuan-2-7b","name":"Baichuan 2-7B","provider":"Baichuan","openWeights":true,"release":"2023-09-20","aliases":["Baichuan-2-7B-Base","Baichuan 2-7B-Base"],"page":null,"best":{"mmlu":{"score":54.16,"unit":"%","sourceType":"paper","date":"2023-09-20","source":"http://arxiv.org/abs/2309.10305"}}},{"id":"baichuan1-7b","name":"Baichuan1-7B","provider":"Baichuan","openWeights":true,"release":"2023-06-01","aliases":["Baichuan-7B","Baichuan 1-7B"],"page":null,"best":{"mmlu":{"score":42.3,"unit":"%","sourceType":"paper","date":"2023-06-01","source":"http://arxiv.org/abs/2309.10305"}}},{"id":"baichuan2-13b","name":"Baichuan2-13B","provider":"Baichuan","openWeights":true,"release":"2023-09-06","aliases":["Baichuan-2-13B-Base","Baichuan 2-13B-Base","Baichuan-2 13B"],"page":null,"best":{"mmlu":{"score":59.17,"unit":"%","sourceType":"paper","date":"2023-09-06","source":"http://arxiv.org/abs/2309.10305"}}},{"id":"baichuan2-13b-chat","name":"Baichuan2-13B-Chat","provider":"Baichuan","openWeights":null,"release":"2023-09-06","aliases":["Baichuan2-Chat 13B"],"page":null,"best":{"mmlu":{"score":55.1,"unit":"%","sourceType":"paper","date":"2023-09-06","source":"http://arxiv.org/abs/2403.04652"}}},{"id":"bielik-11b-v2-3-instruct","name":"Bielik-11B-v2.3-Instruct","provider":"SpeakLeash & ACK Cyfronet AGH","openWeights":true,"release":null,"aliases":["Bielik-11B-v2.3-Instruct (Prompt)"],"page":null,"best":{"bfcl":{"score":21.9,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"bitagent-bounty-8b","name":"BitAgent-Bounty-8B","provider":"Bittensor","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"bfcl":{"score":46.23,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"bloom-1b1","name":"bloom-1b1","provider":"bigscience","openWeights":true,"release":null,"aliases":["bigscience/bloom-1b1"],"page":null,"best":{"open-llm-leaderboard":{"score":4.03,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"bloom-1b7","name":"bloom-1b7","provider":"bigscience","openWeights":true,"release":null,"aliases":["bigscience/bloom-1b7"],"page":null,"best":{"open-llm-leaderboard":{"score":4.05,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"bloom-3b","name":"bloom-3b","provider":"bigscience","openWeights":true,"release":null,"aliases":["bigscience/bloom-3b"],"page":null,"best":{"open-llm-leaderboard":{"score":4.39,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"bloom-560m","name":"bloom-560m","provider":"bigscience","openWeights":true,"release":null,"aliases":["bigscience/bloom-560m"],"page":null,"best":{"open-llm-leaderboard":{"score":3.51,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"bloom-7b1","name":"bloom-7b1","provider":"bigscience","openWeights":true,"release":null,"aliases":["bigscience/bloom-7b1"],"page":null,"best":{"open-llm-leaderboard":{"score":3.8,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"bloomz-mt-176b","name":"Bloomz-mt-176B","provider":"BigScience","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"c-eval":{"score":39,"unit":"%","sourceType":"official","date":"2023-05-15","source":"https://github.com/hkust-nlp/ceval#leaderboard"}}},{"id":"c4ai-aya-expanse-32b","name":"c4ai-aya-expanse-32b","provider":"Cohere","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1267.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"c4ai-aya-expanse-8b","name":"c4ai-aya-expanse-8b","provider":"Cohere","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1223.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"c4ai-aya-vision-32b","name":"c4ai-aya-vision-32b","provider":"Cohere","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-vision":{"score":1000.2,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"c4ai-command-r-08-2024","name":"c4ai-command-r-08-2024","provider":"Cohere","openWeights":null,"release":"2024-08-30","aliases":["Command R"],"page":null,"best":{"mmlu":{"score":65.2,"unit":"%","sourceType":"official","date":"2024-08-30","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"}}},{"id":"c4ai-command-r-plus","name":"c4ai-command-r-plus","provider":"Cohere","openWeights":true,"release":null,"aliases":["CohereForAI/c4ai-command-r-plus"],"page":null,"best":{"open-llm-leaderboard":{"score":30.94,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"c4ai-command-r7b-12-2024","name":"c4ai-command-r7b-12-2024","provider":"Cohere","openWeights":true,"release":null,"aliases":["CohereForAI/c4ai-command-r7b-12-2024"],"page":null,"best":{"open-llm-leaderboard":{"score":31.62,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"cerebras-gpt-13b","name":"Cerebras-GPT-13B","provider":"Cerebras Systems","openWeights":true,"release":"2023-03-20","aliases":[],"page":null,"best":{"mmlu":{"score":26.2,"unit":"%","sourceType":"paper","date":"2023-03-20","source":"http://arxiv.org/abs/2309.03450"}}},{"id":"chatglm-2-6b-base","name":"ChatGLM 2-6B (base)*","provider":"Zhipu AI (Z.ai)","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu":{"score":47.86,"unit":"%","sourceType":"paper","date":"","source":"http://arxiv.org/abs/2309.10305"}}},{"id":"chatglm3-6b","name":"chatglm3-6b","provider":"Zhipu AI (Z.ai)","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1056.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"chatgpt","name":"ChatGPT","provider":"OpenAI","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"c-eval":{"score":54.4,"unit":"%","sourceType":"official","date":"2023-05-15","source":"https://github.com/hkust-nlp/ceval#leaderboard"}}},{"id":"chinchilla","name":"Chinchilla","provider":"Google","openWeights":false,"release":"2022-03-29","aliases":["Chinchilla (70B)","Chinchilla 70B"],"page":null,"best":{"mmlu":{"score":67.5,"unit":"%","sourceType":"paper","date":"2022-03-29","source":"http://arxiv.org/abs/2302.13971"}}},{"id":"chinese-llama-13b","name":"Chinese LLaMA-13B","provider":"Community (Chinese-LLaMA)","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"c-eval":{"score":33.3,"unit":"%","sourceType":"official","date":"2023-05-15","source":"https://github.com/hkust-nlp/ceval#leaderboard"}}},{"id":"chinese-alpaca-13b","name":"Chinese-Alpaca-13B","provider":"Community (Chinese-LLaMA)","openWeights":null,"release":null,"aliases":[],"page":null,"best":{}},{"id":"chinese-alpaca-plus-13b","name":"Chinese-Alpaca-Plus-13B","provider":"Community (Chinese-LLaMA)","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu":{"score":43.9,"unit":"%","sourceType":"paper","date":"","source":"http://arxiv.org/abs/2309.10305"}}},{"id":"claude-1-3","name":"Claude 1.3","provider":"Anthropic","openWeights":false,"release":"2023-04-18","aliases":["claude-1.3"],"page":null,"best":{"mmlu":{"score":77,"unit":"%","sourceType":"vendor","date":"2023-04-18","source":"https://www-cdn.anthropic.com/5c49cc247484cecf107c699baf29250302e5da70/claude-2-model-card.pdf"}}},{"id":"claude-instant","name":"Claude Instant","provider":"Anthropic","openWeights":false,"release":"2023-08-09","aliases":["claude-instant-1.1","Claude instant","Claude Instant 1.1","claude-instant-1.2","Claude Instant 1.2"],"page":null,"best":{"mmlu":{"score":68.8,"unit":"%","sourceType":"official","date":"2023-08-09","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"}}},{"id":"claude-sonnet-3-5-june-2024","name":"Claude Sonnet 3.5 (June 2024)","provider":"Anthropic","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":81.7,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"claude-2-mar-2024","name":"claude-2 (Mar 2024)","provider":"Anthropic","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":61.6,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"claude-3-haiku-mar-2024","name":"claude-3-haiku (Mar 2024)","provider":"Anthropic","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":68.9,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"claude-3-opus-mar-2024","name":"claude-3-opus (Mar 2024)","provider":"Anthropic","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":77.4,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"claude-3-sonnet-mar-2024","name":"claude-3-sonnet (Mar 2024)","provider":"Anthropic","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":64,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"claude-4-5-sonnet","name":"Claude-4.5-Sonnet(Thinking)","provider":"Anthropic","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":87.4,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"claude-4-6-opus","name":"Claude-4.6-Opus(Thinking)","provider":"Anthropic","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":89.1,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"claude-4-6-sonnet","name":"Claude-4.6-Sonnet(Thinking)","provider":"Anthropic","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":87.3,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"claude-instant-1-mar-2024","name":"claude-instant-1 (Mar 2024)","provider":"Anthropic","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":50.6,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"claude-instant-v1-0","name":"Claude-instant-v1.0","provider":"Anthropic","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"c-eval":{"score":45.9,"unit":"%","sourceType":"official","date":"2023-05-15","source":"https://github.com/hkust-nlp/ceval#leaderboard"}}},{"id":"claude-opus-5-5-max","name":"claude-opus-5.5-max","provider":"Anthropic","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-webdev":{"score":1813,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"}}},{"id":"claude-v1-3","name":"Claude-v1.3","provider":"Anthropic","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"c-eval":{"score":54.2,"unit":"%","sourceType":"official","date":"2023-05-15","source":"https://github.com/hkust-nlp/ceval#leaderboard"}}},{"id":"coalm-70b","name":"CoALM-70B","provider":"UIUC + Oumi","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"bfcl":{"score":27.99,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"coalm-8b","name":"CoALM-8B","provider":"UIUC + Oumi","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"bfcl":{"score":26.81,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"code-13b","name":"Code-13B","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":52.4,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"code-290k-6-7b-instruct","name":"Code-290k-6.7B-Instruct","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":59.7,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"code-33b","name":"Code-33B","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":49.4,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"code-millenials-34b","name":"code-millenials-34B","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":70.7,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"codegemma-1-1-2b","name":"codegemma-1.1-2b","provider":"Google","openWeights":true,"release":null,"aliases":["google/codegemma-1.1-2b"],"page":null,"best":{"open-llm-leaderboard":{"score":7.13,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"codegemma-2b","name":"codegemma-2b","provider":"Google","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":20.7,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"codegemma-7b","name":"codegemma-7b","provider":"Google","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":41.5,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"codegemma-7b-it","name":"codegemma-7b-it","provider":"Google","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":51.8,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"codegen-16b","name":"CodeGen-16B","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":28,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"codegen-2b","name":"CodeGen-2B","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":22.6,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"codegen-6b","name":"CodeGen-6B","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":25.6,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"codegen2-16b","name":"CodeGen2-16B","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":16.5,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"codegen2-1b","name":"CodeGen2-1B","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":9.1,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"codegen2-3b","name":"CodeGen2-3B","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":12.8,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"codegen2-7b","name":"CodeGen2-7B","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":17.7,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"codellama-13b","name":"CodeLlama-13B","provider":"Meta","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":38.4,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"codellama-34b","name":"CodeLlama-34B","provider":"Meta","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":43.9,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"codellama-34b-instruct","name":"codellama-34b-instruct","provider":"Meta","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1136.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"codellama-70b","name":"CodeLlama-70B","provider":"Meta","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":50.6,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"codellama-7b","name":"CodeLlama-7B","provider":"Meta","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":35.4,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"codeqwen1-5-7b-chat","name":"CodeQwen1.5-7B-Chat","provider":"Alibaba (Qwen)","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":78.7,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"codet5-16b","name":"CodeT5+-16B","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":26.8,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"codet5-2b","name":"CodeT5+-2B","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":22,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"codet5-6b","name":"CodeT5+-6B","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":24.4,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"cogvlm2-llama3-chat-19b","name":"cogvlm2-llama3-chat-19b","provider":"Zhipu AI (Z.ai)","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-vision":{"score":963.7,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"cohere-aya-vision","name":"Cohere-Aya-Vision","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":47.2,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"collectivecognition-v1-1-mistral-7b","name":"CollectiveCognition-v1.1-Mistral-7B","provider":"teknium","openWeights":true,"release":null,"aliases":["teknium/CollectiveCognition-v1.1-Mistral-7B"],"page":null,"best":{"open-llm-leaderboard":{"score":14.26,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"command-a","name":"Command A Reasoning","provider":"Cohere","openWeights":true,"release":null,"aliases":["Command A Reasoning (FC)","Command A (FC)"],"page":null,"best":{"bfcl":{"score":57.06,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"command-r7b","name":"Command R7B","provider":"Cohere","openWeights":true,"release":null,"aliases":["Command R7B (FC)"],"page":null,"best":{"bfcl":{"score":32.07,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"command-a-03-2025","name":"command-a-03-2025","provider":"Cohere","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1353.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"command-r-08-2024","name":"command-r-08-2024","provider":"Cohere","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1250.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"command-r-plus","name":"command-r-plus","provider":"Cohere","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1261.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"command-r-plus-08-2024","name":"command-r-plus-08-2024","provider":"Cohere","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1276.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"computer-use-preview","name":"computer-use-preview-2025-03-11","provider":null,"openWeights":null,"release":"2025-03-11","aliases":[],"page":null,"best":{"osworld":{"score":31.3,"unit":"%","sourceType":"official","date":"2025-07-27","source":"https://os-world.github.io/"}}},{"id":"davinci-002","name":"davinci-002","provider":"OpenAI","openWeights":false,"release":"2022-03-15","aliases":["text-davinci-002","GPT-3.5"],"page":null,"best":{"mmlu":{"score":70,"unit":"%","sourceType":"paper","date":"2022-03-15","source":"https://arxiv.org/pdf/2303.08774"}}},{"id":"dbrx-instruct-preview","name":"dbrx-instruct-preview","provider":"Databricks","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1195.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"dclm-7b","name":"DCLM-7B","provider":"apple","openWeights":true,"release":null,"aliases":["apple/DCLM-7B"],"page":null,"best":{"open-llm-leaderboard":{"score":14.11,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"decilm-7b","name":"DeciLM-7B","provider":"Deci","openWeights":true,"release":null,"aliases":["Deci/DeciLM-7B"],"page":null,"best":{"open-llm-leaderboard":{"score":15.02,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"decilm-7b-instruct","name":"DeciLM-7B-instruct","provider":"Deci","openWeights":true,"release":null,"aliases":["Deci/DeciLM-7B-instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":17.47,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"deephermes-3-mistral-24b-preview","name":"DeepHermes-3-Mistral-24B-Preview","provider":"NousResearch","openWeights":true,"release":null,"aliases":["NousResearch/DeepHermes-3-Mistral-24B-Preview"],"page":null,"best":{"open-llm-leaderboard":{"score":31.99,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"deepseek-llm-chat-67b","name":"DeepSeek LLM Chat (67B)","provider":"DeepSeek","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu":{"score":72.5,"unit":"%","sourceType":"official","date":"","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"}}},{"id":"deepseek-chat-v2-5","name":"DeepSeek-Chat-V2_5","provider":"DeepSeek","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":65.83,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"deepseek-coder-7b-instruct-v1-5","name":"DeepSeek-Coder-7B-instruct-v1.5","provider":"DeepSeek","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":71.3,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"deepseek-coder-v2","name":"deepseek-coder-v2","provider":"DeepSeek","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1265.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"deepseek-coder-v2-lite-instruct","name":"DeepSeek-Coder-V2-Lite-Instruct","provider":"DeepSeek","openWeights":null,"release":"2024-06-13","aliases":[],"page":null,"best":{"mmlu-pro":{"score":41.57,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"deepseek-llm-7b","name":"deepseek-llm-7b-chat","provider":"DeepSeek","openWeights":true,"release":null,"aliases":["deepseek-ai/deepseek-llm-7b-chat","deepseek-ai/deepseek-llm-7b-base"],"page":null,"best":{"open-llm-leaderboard":{"score":14.82,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"deepseek-moe-16b-base","name":"deepseek-moe-16b-base","provider":"DeepSeek","openWeights":true,"release":null,"aliases":["deepseek-ai/deepseek-moe-16b-base"],"page":null,"best":{"open-llm-leaderboard":{"score":7.47,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"deepseek-moe-16b-chat","name":"deepseek-moe-16b-chat","provider":"DeepSeek","openWeights":true,"release":null,"aliases":["deepseek-ai/deepseek-moe-16b-chat"],"page":null,"best":{"open-llm-leaderboard":{"score":10.29,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"deepseek-r1-distill-llama-8b","name":"DeepSeek-R1-Distill-Llama-8B","provider":"DeepSeek","openWeights":true,"release":null,"aliases":["deepseek-ai/DeepSeek-R1-Distill-Llama-8B"],"page":null,"best":{"open-llm-leaderboard":{"score":13.06,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"deepseek-r1-distill-qwen-7b","name":"DeepSeek-R1-Distill-Qwen-7B","provider":"DeepSeek","openWeights":true,"release":null,"aliases":["deepseek-ai/DeepSeek-R1-Distill-Qwen-7B"],"page":null,"best":{"open-llm-leaderboard":{"score":14.99,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"deepseek-v2-moe-236b-may-2024","name":"DeepSeek-V2 (MoE-236B, May 2024)","provider":"DeepSeek","openWeights":true,"release":"2024-05-07","aliases":["DeepSeek-V2","DeepSeek-V2 Base"],"page":null,"best":{"mmlu":{"score":78.4,"unit":"%","sourceType":"paper","date":"2024-05-07","source":"https://arxiv.org/pdf/2412.19437"}}},{"id":"deepseek-v2-chat","name":"Deepseek-V2-Chat","provider":"DeepSeek","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":54.81,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"deepseek-v2-5-sep-2024","name":"deepseek-v2.5","provider":"DeepSeek","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1307.2,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"deepseek-v2-5-nov-2024","name":"DeepSeek-V2.5 (Nov 2024)","provider":"DeepSeek","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":83.5,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"deepseek-v2-5-dec-2024","name":"deepseek-v2.5-1210","provider":"DeepSeek","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1323.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"deepseek-v3-nov-2024","name":"DeepSeek-V3 (Nov 2024)","provider":"DeepSeek","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":86.6,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"deepseek-v3-1-nonthinking","name":"DeepSeek-V3.1-NonThinking","provider":"DeepSeek","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":83.7,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"deepseek-v3-1-terminus","name":"deepseek-v3.1-terminus-thinking","provider":"DeepSeek","openWeights":true,"release":null,"aliases":["deepseek-v3.1-terminus"],"page":null,"best":{"lmarena-text":{"score":1416,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"deepseek-v3-2-exp-prompt-thinking","name":"DeepSeek-V3.2-Exp (Prompt + Thinking)","provider":"DeepSeek","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"bfcl":{"score":56.73,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"deepseek-v3-2-reasoner","name":"deepseek-v3.2-reasoner","provider":"DeepSeek","openWeights":null,"release":null,"aliases":["DeepSeek V3.2 Reasoner"],"page":null,"best":{"swe-bench-verified":{"score":60,"unit":"%","sourceType":"official","date":"2025-12-01","source":"https://www.swebench.com/#verified"}}},{"id":"deepseekmath-7b-instruct","name":"DeepseekMath-7B-Instruct","provider":"DeepSeek","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":35.3,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"devstral-small-2","name":"Devstral Small 2","provider":"Mistral AI","openWeights":true,"release":"2025-12-09","aliases":["devstral-small-2512","Devstral Small (2512)"],"page":null,"best":{"swe-bench-verified":{"score":56.4,"unit":"%","sourceType":"official","date":"2025-12-09","source":"https://www.swebench.com/#verified"}}},{"id":"devstral-2","name":"devstral-2","provider":"Mistral AI","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-webdev":{"score":1196.6,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"}}},{"id":"devstral-2512","name":"devstral-2512","provider":"Mistral AI","openWeights":null,"release":null,"aliases":["Devstral (2512)"],"page":null,"best":{"swe-bench-verified":{"score":53.8,"unit":"%","sourceType":"official","date":"2025-12-09","source":"https://www.swebench.com/#verified"}}},{"id":"devstral-medium-2507","name":"devstral-medium-2507","provider":"Mistral AI","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-webdev":{"score":1076.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"}}},{"id":"devstral-small","name":"Devstral-Small-2505","provider":"Mistral AI","openWeights":null,"release":null,"aliases":["mistralai/Devstral-Small-2505","DevStral Small 2505","OpenHands + DevStral Small 2505"],"page":null,"best":{"swe-bench-verified":{"score":46.8,"unit":"%","sourceType":"official","date":"2025-05-20","source":"https://www.swebench.com/#verified"}}},{"id":"devstral-small-2507","name":"devstral-small-2507","provider":"Mistral AI","openWeights":null,"release":null,"aliases":["DevStral Small 2507","SWE-agent + DevStral Small 2507"],"page":null,"best":{"swe-bench-verified":{"score":38,"unit":"%","sourceType":"official","date":"2025-07-25","source":"https://www.swebench.com/#verified"}}},{"id":"dialogpt","name":"DialoGPT-medium","provider":"Microsoft","openWeights":true,"release":null,"aliases":["microsoft/DialoGPT-medium"],"page":null,"best":{"open-llm-leaderboard":{"score":5.25,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"distyl-buttonagent","name":"Distyl ButtonAgent","provider":"Distyl AI","openWeights":null,"release":null,"aliases":[],"page":null,"best":{}},{"id":"dolly-v1-6b","name":"dolly-v1-6b","provider":"databricks","openWeights":true,"release":null,"aliases":["databricks/dolly-v1-6b"],"page":null,"best":{"open-llm-leaderboard":{"score":6.98,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"dolly-v2-3b","name":"dolly-v2-3b","provider":"databricks","openWeights":true,"release":null,"aliases":["databricks/dolly-v2-3b"],"page":null,"best":{"open-llm-leaderboard":{"score":5.6,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"dolly-v2-7b","name":"dolly-v2-7b","provider":"databricks","openWeights":true,"release":null,"aliases":["databricks/dolly-v2-7b"],"page":null,"best":{"open-llm-leaderboard":{"score":5.65,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"dolphin-2-2-1-mistral-7b","name":"dolphin-2.2.1-mistral-7b","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1152.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"dolphin-2-6-mixtral-8x7b","name":"dolphin-2.6-mixtral-8x7b","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":57.3,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"doubao-1-5-pro","name":"Doubao-1.5-Pro","provider":"ByteDance","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":80.1,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"echo-ego-v2-14b","name":"ECHO_Ego_v2_14B","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":71.24,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"ernie-4-5-21b-a3b-base","name":"ERNIE-4.5-21B-A3B-Base","provider":"Baidu","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":56.7,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"ernie-4-5-300b-a47b","name":"ERNIE-4.5-300B-A47B","provider":"Baidu","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":78.4,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"ernie-4-5-300b-a47b-base","name":"ERNIE-4.5-300B-A47B-Base","provider":"Baidu","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":69.5,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"ernie-5-0-0110","name":"ernie-5.0-0110","provider":"Baidu","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1446.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"ernie-5-0-preview-1022","name":"ernie-5.0-preview-1022","provider":"Baidu","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1418.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"ernie-5-0-preview-1203","name":"ernie-5.0-preview-1203","provider":"Baidu","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1448.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"ernie-5-0-preview-1220","name":"ernie-5.0-preview-1220","provider":"Baidu","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-vision":{"score":1218.9,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"ernie-5-1","name":"ernie-5.1","provider":"Baidu","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1467.2,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"eurus-2-7b-prime","name":"Eurus-2-7B-PRIME","provider":"Tsinghua University","openWeights":true,"release":"2024-12-31","aliases":[],"page":null,"best":{"gpqa-diamond":{"score":33.9,"unit":"%","sourceType":"independent","date":"2025-01-27","source":"https://epoch.ai/benchmarks"}}},{"id":"exaone-3-0-7-8b-instruct","name":"EXAONE-3.0-7.8B-Instruct","provider":"LGAI-EXAONE","openWeights":true,"release":null,"aliases":["LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":25.73,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"exaone-4-0-32b","name":"EXAONE-4.0-32B","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"livecodebench":{"score":66.6,"unit":"%","sourceType":"official","date":"2025-04-07","source":"https://livecodebench.github.io/leaderboard.html"}}},{"id":"falcon-180b","name":"Falcon-180B","provider":"Technology Innovation Institute","openWeights":true,"release":"2023-09-06","aliases":["falcon-180B"],"page":null,"best":{"mmlu":{"score":70.6,"unit":"%","sourceType":"paper","date":"2023-09-06","source":"http://arxiv.org/abs/2311.16867"}}},{"id":"falcon-180b-chat","name":"falcon-180b-chat","provider":"TII","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1148.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"falcon-7b-instruct","name":"falcon-7b-instruct","provider":"TII","openWeights":true,"release":null,"aliases":["tiiuae/falcon-7b-instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":5.12,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"falcon-mamba-7b","name":"falcon-mamba-7b","provider":"TII","openWeights":true,"release":null,"aliases":["tiiuae/falcon-mamba-7b"],"page":null,"best":{"open-llm-leaderboard":{"score":15.18,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"falcon-rw-1-3b","name":"Falcon-rw-1.3B","provider":"TII","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu":{"score":25.9,"unit":"%","sourceType":"paper","date":"","source":"http://arxiv.org/abs/2309.05463"}}},{"id":"falcon3-10b-base","name":"Falcon3-10B-Base","provider":"TII","openWeights":true,"release":null,"aliases":["tiiuae/Falcon3-10B-Base"],"page":null,"best":{"open-llm-leaderboard":{"score":27.62,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"falcon3-1b-base","name":"Falcon3-1B-Base","provider":"TII","openWeights":true,"release":null,"aliases":["tiiuae/Falcon3-1B-Base"],"page":null,"best":{"open-llm-leaderboard":{"score":9.89,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"falcon3-3b-base","name":"Falcon3-3B-Base","provider":"TII","openWeights":true,"release":null,"aliases":["tiiuae/Falcon3-3B-Base"],"page":null,"best":{"open-llm-leaderboard":{"score":15.74,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"falcon3-7b-base","name":"Falcon3-7B-Base","provider":"TII","openWeights":true,"release":null,"aliases":["tiiuae/Falcon3-7B-Base"],"page":null,"best":{"open-llm-leaderboard":{"score":24.75,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"falcon3-mamba-7b-base","name":"Falcon3-Mamba-7B-Base","provider":"TII","openWeights":true,"release":null,"aliases":["tiiuae/Falcon3-Mamba-7B-Base"],"page":null,"best":{"open-llm-leaderboard":{"score":18.14,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"falcon3-mamba-7b-instruct","name":"Falcon3-Mamba-7B-Instruct","provider":"TII","openWeights":true,"release":null,"aliases":["tiiuae/Falcon3-Mamba-7B-Instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":28.11,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"fastchat-t5-3b","name":"fastchat-t5-3b","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":992.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"flan-t5-base","name":"flan-t5-base","provider":"Google","openWeights":true,"release":null,"aliases":["google/flan-t5-base"],"page":null,"best":{"open-llm-leaderboard":{"score":6.42,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"flan-t5-large","name":"flan-t5-large","provider":"Google","openWeights":true,"release":null,"aliases":["google/flan-t5-large"],"page":null,"best":{"open-llm-leaderboard":{"score":9.66,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"flan-t5-small","name":"flan-t5-small","provider":"Google","openWeights":true,"release":null,"aliases":["google/flan-t5-small"],"page":null,"best":{"open-llm-leaderboard":{"score":6.13,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"flan-t5-xl","name":"flan-t5-xl","provider":"Google","openWeights":true,"release":null,"aliases":["google/flan-t5-xl"],"page":null,"best":{"open-llm-leaderboard":{"score":11.71,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"flan-t5-xxl","name":"flan-t5-xxl","provider":"Google","openWeights":true,"release":null,"aliases":["google/flan-t5-xxl"],"page":null,"best":{"open-llm-leaderboard":{"score":13.66,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"flan-ul2","name":"flan-ul2","provider":"Google","openWeights":true,"release":null,"aliases":["google/flan-ul2"],"page":null,"best":{"open-llm-leaderboard":{"score":13.68,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"frogboss-32b-2510","name":"FrogBoss-32B-2510","provider":null,"openWeights":null,"release":null,"aliases":["Frogboss 32B 2510"],"page":null,"best":{"swe-bench-verified":{"score":53.6,"unit":"%","sourceType":"official","date":"2025-11-10","source":"https://www.swebench.com/#verified"}}},{"id":"frogmini-14b-2510","name":"FrogMini-14B-2510","provider":null,"openWeights":null,"release":null,"aliases":["Frogmini 14B 2510"],"page":null,"best":{"swe-bench-verified":{"score":45,"unit":"%","sourceType":"official","date":"2025-11-10","source":"https://www.swebench.com/#verified"}}},{"id":"gemini-1-5-pro-0409-preview","name":"Gemini 1.5 Pro (0409 preview)","provider":"Google","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu":{"score":81,"unit":"%","sourceType":"official","date":"","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"}}},{"id":"gemini-1-5-pro-feb-2024","name":"Gemini 1.5 Pro (Feb 2024)","provider":"Google","openWeights":false,"release":"2024-02-15","aliases":["gemini-1.5-pro-001-feb24","Gemini 1.5 Pro (001)"],"page":null,"best":{"mmlu":{"score":82.7,"unit":"%","sourceType":"official","date":"2024-02-15","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"}}},{"id":"gemini-3-0-pro","name":"Gemini 3.0 Pro","provider":"Google","openWeights":null,"release":"2025-11-18","aliases":[],"page":null,"best":{"tau2-bench":{"score":85.3,"unit":"%","sourceType":"official","date":"2025-11-18","source":"https://taubench.com/"}}},{"id":"gemini-4-argon-provider-adapter","name":"Gemini 4 Argon - Provider Adapter (Low)","provider":"Google","openWeights":null,"release":"2026-10-13","aliases":["Gemini 4 Argon - Provider Adapter (Medium)","Gemini 4 Argon - Provider Adapter (High)"],"page":null,"best":{"arc-agi-3":{"score":97.5,"unit":"%","sourceType":"official","date":"2026-10-22","source":"https://arcprize.org/leaderboard"}}},{"id":"gemini-pro-1-0","name":"Gemini Pro 1.0","provider":"Google","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":55.5,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"gemini-pro-1-5","name":"Gemini Pro 1.5","provider":"Google","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":61,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"gemini-1-5-flash","name":"Gemini-1.5-Flash","provider":"Google","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":59.12,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"gemini-1-5-pro","name":"Gemini-1.5-Pro","provider":"Google","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":69.03,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"gemini-2-5-flash-lite","name":"Gemini-2.5-Flash-Lite","provider":"Google","openWeights":false,"release":null,"aliases":["Gemini-2.5-Flash-Lite (FC)","Gemini-2.5-Flash-Lite (Prompt)"],"page":null,"best":{"bfcl":{"score":36.87,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"gemini-advanced-0514","name":"gemini-advanced-0514","provider":"Google","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1335.9,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"gemini-pro","name":"gemini-pro","provider":"Google","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1223.6,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"gemini-pro-dev-api","name":"gemini-pro-dev-api","provider":"Google","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1236.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"gemma-2-2b","name":"gemma-2-2b","provider":"Google","openWeights":true,"release":null,"aliases":["google/gemma-2-2b"],"page":null,"best":{"open-llm-leaderboard":{"score":10.36,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"gemma-2-2b-jpn-it","name":"gemma-2-2b-jpn-it","provider":"Google","openWeights":true,"release":null,"aliases":["google/gemma-2-2b-jpn-it"],"page":null,"best":{"open-llm-leaderboard":{"score":17.12,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"gemma-2-9b-it-simpo","name":"gemma-2-9b-it-simpo","provider":"Google","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1280.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"gemma-3n-e4b-it","name":"gemma-3n-e4b-it","provider":"Google","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1317.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"general-reasoner-14b","name":"General-Reasoner-14B","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":66.6,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"general-reasoner-7b","name":"General-Reasoner-7B","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":58.9,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"glm-130b","name":"GLM-130B","provider":"Zhipu AI (Z.ai)","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"c-eval":{"score":40.3,"unit":"%","sourceType":"official","date":"2023-05-15","source":"https://github.com/hkust-nlp/ceval#leaderboard"}}},{"id":"glm-4-0520","name":"GLM-4 (0520)","provider":"Zhipu AI (Z.ai)","openWeights":false,"release":"2024-05-20","aliases":["glm-4-0520"],"page":null,"best":{"lmarena-text":{"score":1273.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"glm-4-9b-chat-1m","name":"glm-4-9b-chat-1m","provider":"Zhipu AI (Z.ai)","openWeights":true,"release":null,"aliases":["THUDM/glm-4-9b-chat-1m"],"page":null,"best":{"open-llm-leaderboard":{"score":8.92,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"glm-4-9b-chat-1m-hf","name":"glm-4-9b-chat-1m-hf","provider":"Zhipu AI (Z.ai)","openWeights":true,"release":null,"aliases":["THUDM/glm-4-9b-chat-1m-hf"],"page":null,"best":{"open-llm-leaderboard":{"score":15.14,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"glm-4-9b-chat-hf","name":"glm-4-9b-chat-hf","provider":"Zhipu AI (Z.ai)","openWeights":true,"release":null,"aliases":["THUDM/glm-4-9b-chat-hf"],"page":null,"best":{"open-llm-leaderboard":{"score":20.54,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"glm-4-plus","name":"glm-4-plus","provider":"Zhipu AI (Z.ai)","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1319.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"glm-4-plus-0111","name":"glm-4-plus-0111","provider":"Zhipu AI (Z.ai)","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1342.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"gopher-280b","name":"Gopher (280B)","provider":"Google","openWeights":false,"release":"2021-12-08","aliases":["Gopher","Gopher 280B"],"page":null,"best":{"mmlu":{"score":60,"unit":"%","sourceType":"paper","date":"2021-12-08","source":"http://arxiv.org/abs/2112.11446"}}},{"id":"gpt-4o-mini-july-2024","name":"GPT 4o Mini (July 2024)","provider":"OpenAI","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":83.5,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"gpt-3-5-may-2023","name":"GPT-3.5 (May 2023)","provider":"OpenAI","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":66.5,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"gpt-3-5-turbo","name":"GPT-3.5 Turbo","provider":"OpenAI","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu":{"score":68.54,"unit":"%","sourceType":"paper","date":"","source":"http://arxiv.org/abs/2309.10305"}}},{"id":"gpt-3-5-turbo-jun-2023","name":"GPT-3.5 Turbo (Jun 2023)","provider":"OpenAI","openWeights":false,"release":"2023-06-13","aliases":["gpt-3.5-turbo-0613","GPT-3.5 Turbo (June 2023)","GPT-3.5 Turbo (0613)"],"page":null,"best":{"mmlu":{"score":68.9,"unit":"%","sourceType":"official","date":"2023-06-13","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"}}},{"id":"gpt-4-may-2023","name":"GPT-4 (May 2023)","provider":"OpenAI","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":79.3,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"gpt-4-mini","name":"GPT-4-mini (high)","provider":"OpenAI","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":83,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"gpt-4-turbo-april-2024","name":"GPT-4-Turbo (April 2024)","provider":"OpenAI","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":86.6,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"gpt-5-pro","name":"GPT-5 Pro","provider":"OpenAI","openWeights":false,"release":"2025-10-07","aliases":["gpt-5-pro-2025-10-06_unknown","gpt-5-pro-2025-10-06"],"page":null,"best":{"hle":{"score":31.64,"unit":"%","sourceType":"compiled","date":"2025-10-07","source":"https://epoch.ai/benchmarks"}}},{"id":"gpt-5-codex","name":"GPT-5-Codex","provider":"OpenAI","openWeights":false,"release":"2025-09-15","aliases":["gpt-5-codex","GPT-5-codex"],"page":null,"best":{"terminal-bench":{"score":44.33,"unit":"%","sourceType":"official","date":"2025-09-15","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"}}},{"id":"gpt-5-1-codex-max","name":"GPT-5.1-Codex-Max","provider":"OpenAI","openWeights":false,"release":"2025-11-19","aliases":["gpt-5.1-codex-max"],"page":null,"best":{"terminal-bench":{"score":60.45,"unit":"%","sourceType":"official","date":"2025-11-19","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"}}},{"id":"gpt-5-3-chat-latest","name":"gpt-5.3-chat-latest","provider":"OpenAI","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1450.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"gpt-5-3-codex-codex-harness","name":"gpt-5.3-codex (codex-harness)","provider":"OpenAI","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-webdev":{"score":1408.6,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"}}},{"id":"gpt-5-4-high-codex-harness","name":"gpt-5.4-high (codex-harness)","provider":"OpenAI","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-webdev":{"score":1465.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"}}},{"id":"gpt-5-4-medium-codex-harness","name":"gpt-5.4-medium (codex-harness)","provider":"OpenAI","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-webdev":{"score":1444.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"}}},{"id":"gpt-5-5-codex-harness","name":"gpt-5.5 (codex-harness)","provider":"OpenAI","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-webdev":{"score":1455.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"}}},{"id":"gpt-5-5-high-codex-harness","name":"gpt-5.5-high (codex-harness)","provider":"OpenAI","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-webdev":{"score":1487.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"}}},{"id":"gpt-5-5-xhigh-codex-harness","name":"gpt-5.5-xhigh (codex-harness)","provider":"OpenAI","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-webdev":{"score":1512.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"}}},{"id":"gpt-5-6-luna-xhigh-codex-harness","name":"gpt-5.6-luna-xhigh (codex-harness)","provider":"OpenAI","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-webdev":{"score":1519,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"}}},{"id":"gpt-5-6-sol-xhigh-codex-harness","name":"gpt-5.6-sol-xhigh (codex-harness)","provider":"OpenAI","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-webdev":{"score":1618.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"}}},{"id":"gpt-5-6-terra-xhigh-codex-harness","name":"gpt-5.6-terra-xhigh (codex-harness)","provider":"OpenAI","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-webdev":{"score":1521.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"}}},{"id":"gpt-6-astra-provider-adapter","name":"GPT-6 Astra - Provider Adapter (High)","provider":"OpenAI","openWeights":null,"release":"2026-09-02","aliases":["GPT-6 Astra - Provider Adapter (Max)","GPT-6 Astra - Provider Adapter (XHigh)","GPT-6 Astra - Provider Adapter (Medium)","GPT-6 Astra - Provider Adapter (Low)","GPT-6 Astra - Provider Adapter (None)"],"page":null,"best":{"arc-agi-3":{"score":99.9,"unit":"%","sourceType":"official","date":"2026-10-22","source":"https://arcprize.org/leaderboard"}}},{"id":"gpt-6-1-sol-provider-adapter","name":"GPT-6.1 Sol - Provider Adapter (XHigh)","provider":"OpenAI","openWeights":null,"release":"2026-09-29","aliases":[],"page":null,"best":{"arc-agi-3":{"score":96.4,"unit":"%","sourceType":"official","date":"2026-10-22","source":"https://arcprize.org/leaderboard"}}},{"id":"gpt-neo-1-3b","name":"gpt-neo-1.3B","provider":"EleutherAI","openWeights":true,"release":null,"aliases":["EleutherAI/gpt-neo-1.3B"],"page":null,"best":{"open-llm-leaderboard":{"score":5.39,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"gpt-neo-125m","name":"gpt-neo-125m","provider":"EleutherAI","openWeights":true,"release":null,"aliases":["EleutherAI/gpt-neo-125m"],"page":null,"best":{"open-llm-leaderboard":{"score":4.41,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"gpt-o1","name":"GPT-o1","provider":"OpenAI","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":89.3,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"gpt-o1-mini","name":"GPT-o1-mini","provider":"OpenAI","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":80.3,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"gpt-o3","name":"GPT-o3-high","provider":"OpenAI","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":85,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"gpt-o3-mini","name":"GPT-o3-mini","provider":"OpenAI","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":79.4,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"gpt4all-13b-snoozy","name":"gpt4all-13b-snoozy","provider":"OpenAI","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1067.6,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"granite-20b-functioncalling","name":"Granite-20b-FunctionCalling","provider":"IBM","openWeights":true,"release":null,"aliases":["Granite-20b-FunctionCalling (FC)"],"page":null,"best":{"bfcl":{"score":23.23,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"granite-3-0-1b-a400m-base","name":"granite-3.0-1b-a400m-base","provider":"IBM","openWeights":true,"release":null,"aliases":["ibm-granite/granite-3.0-1b-a400m-base"],"page":null,"best":{"open-llm-leaderboard":{"score":6.03,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"granite-3-0-1b-a400m-instruct","name":"granite-3.0-1b-a400m-instruct","provider":"IBM","openWeights":true,"release":null,"aliases":["ibm-granite/granite-3.0-1b-a400m-instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":8.07,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"granite-3-0-3b-a800m-base","name":"granite-3.0-3b-a800m-base","provider":"IBM","openWeights":true,"release":null,"aliases":["ibm-granite/granite-3.0-3b-a800m-base"],"page":null,"best":{"open-llm-leaderboard":{"score":9.49,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"granite-3-0-3b-a800m-instruct","name":"granite-3.0-3b-a800m-instruct","provider":"IBM","openWeights":true,"release":null,"aliases":["ibm-granite/granite-3.0-3b-a800m-instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":13.7,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"granite-3-2-2b-instruct","name":"granite-3.2-2b-instruct","provider":"IBM","openWeights":true,"release":null,"aliases":["ibm-granite/granite-3.2-2b-instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":21.25,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"granite-4-2-30b","name":"granite-4.2-30b","provider":"IBM","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1339.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"granite-4-2-3b","name":"granite-4.2-3b","provider":"IBM","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1289.6,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"granite-4-2-8b","name":"granite-4.2-8b","provider":"IBM","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1290.2,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"granite-7b-base","name":"granite-7b-base","provider":"IBM","openWeights":true,"release":null,"aliases":["ibm-granite/granite-7b-base"],"page":null,"best":{"open-llm-leaderboard":{"score":7.91,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"granite-7b-instruct","name":"granite-7b-instruct","provider":"IBM","openWeights":true,"release":null,"aliases":["ibm-granite/granite-7b-instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":12.03,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"grok-4-2","name":"Grok 4.2","provider":"xAI","openWeights":null,"release":"2026-03-10","aliases":[],"page":null,"best":{}},{"id":"grok-beta","name":"Grok Beta","provider":"xAI","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":80.5,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"grok-3-preview-02-24","name":"grok-3-preview-02-24","provider":"xAI","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1411.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"grok-4-fast-chat","name":"grok-4-fast-chat","provider":"xAI","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1418.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"grok-4-1-fast-non-reasoning","name":"Grok-4.1-Fast(Non-Reasoning)","provider":"xAI","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":75.2,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"grok-4-20-beta1","name":"grok-4.20-beta1","provider":"xAI","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1474.6,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"grok3-beta","name":"Grok3-Beta","provider":"xAI","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":79.9,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"grok3-mini-beta","name":"Grok3-mini-Beta","provider":"xAI","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":78.9,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"guanaco-33b","name":"guanaco-33b","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1127.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"hammer2-1-0-5b","name":"Hammer2.1-0.5b","provider":"MadeAgents","openWeights":true,"release":null,"aliases":["Hammer2.1-0.5b (FC)"],"page":null,"best":{"bfcl":{"score":21.22,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"hammer2-1-1-5b","name":"Hammer2.1-1.5b","provider":"MadeAgents","openWeights":true,"release":null,"aliases":["Hammer2.1-1.5b (FC)"],"page":null,"best":{"bfcl":{"score":27.88,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"hammer2-1-3b","name":"Hammer2.1-3b","provider":"MadeAgents","openWeights":true,"release":null,"aliases":["Hammer2.1-3b (FC)"],"page":null,"best":{"bfcl":{"score":29.71,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"hammer2-1-7b","name":"Hammer2.1-7b","provider":"MadeAgents","openWeights":true,"release":null,"aliases":["Hammer2.1-7b (FC)"],"page":null,"best":{"bfcl":{"score":31.67,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"hermes-2-pro-llama-3-8b","name":"Hermes-2-Pro-Llama-3-8B","provider":"NousResearch","openWeights":true,"release":null,"aliases":["NousResearch/Hermes-2-Pro-Llama-3-8B"],"page":null,"best":{"open-llm-leaderboard":{"score":22.07,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"hermes-2-pro-mistral-7b","name":"Hermes-2-Pro-Mistral-7B","provider":"NousResearch","openWeights":true,"release":null,"aliases":["NousResearch/Hermes-2-Pro-Mistral-7B"],"page":null,"best":{"open-llm-leaderboard":{"score":21.84,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"hermes-2-theta-llama-3-8b","name":"Hermes-2-Theta-Llama-3-8B","provider":"NousResearch","openWeights":true,"release":null,"aliases":["NousResearch/Hermes-2-Theta-Llama-3-8B"],"page":null,"best":{"open-llm-leaderboard":{"score":24.79,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"hermes-3-llama-3-1-70b","name":"Hermes-3-Llama-3.1-70B","provider":"NousResearch","openWeights":true,"release":null,"aliases":["NousResearch/Hermes-3-Llama-3.1-70B"],"page":null,"best":{"open-llm-leaderboard":{"score":38.51,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"hermes-3-llama-3-1-8b","name":"Hermes-3-Llama-3.1-8B","provider":"NousResearch","openWeights":true,"release":null,"aliases":["NousResearch/Hermes-3-Llama-3.1-8B"],"page":null,"best":{"open-llm-leaderboard":{"score":23.49,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"hermes-3-llama-3-2-3b","name":"Hermes-3-Llama-3.2-3B","provider":"NousResearch","openWeights":true,"release":null,"aliases":["NousResearch/Hermes-3-Llama-3.2-3B"],"page":null,"best":{"open-llm-leaderboard":{"score":15.24,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"higgs-llama-3-70b","name":"Higgs-Llama-3-70B","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":63.16,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"hunyuan-a13b","name":"Hunyuan-A13B","provider":"Tencent","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":67.3,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"hunyuan-standard","name":"hunyuan-standard-2025-02-10","provider":"Tencent","openWeights":false,"release":null,"aliases":["hunyuan-standard-256k"],"page":null,"best":{"lmarena-text":{"score":1311.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"hunyuan-standard-vision","name":"hunyuan-standard-vision-2024-12-31","provider":"Tencent","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-vision":{"score":1041.7,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"hunyuan-turbo-0110","name":"hunyuan-turbo-0110","provider":"Tencent","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1340.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"hunyuan-turbos","name":"hunyuan-turbos","provider":"Tencent","openWeights":false,"release":null,"aliases":["hunyuan-turbos-20250416","hunyuan-turbos-20250226"],"page":null,"best":{"lmarena-text":{"score":1383.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"hunyuanturbos","name":"HunyuanTurboS","provider":"Tencent","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":79,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"tencent-hy4-preview","name":"hy4-preview","provider":"Tencent","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-webdev":{"score":1631.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"}}},{"id":"hymba-1-5b-base","name":"Hymba-1.5B-Base","provider":"NVIDIA","openWeights":true,"release":null,"aliases":["nvidia/Hymba-1.5B-Base"],"page":null,"best":{"open-llm-leaderboard":{"score":8.04,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"hymba-1-5b-instruct","name":"Hymba-1.5B-Instruct","provider":"NVIDIA","openWeights":true,"release":null,"aliases":["nvidia/Hymba-1.5B-Instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":14.19,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"ibm-granite-h-small","name":"ibm-granite-h-small","provider":"IBM","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1287.2,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"incoder-1-3b","name":"InCoder-1.3B","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":11,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"incoder-6-7b","name":"InCoder-6.7B","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":12.2,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"inflection-1","name":"Inflection-1","provider":"Inflection AI","openWeights":false,"release":"2023-06-22","aliases":["Inflection 1"],"page":null,"best":{"mmlu":{"score":72.7,"unit":"%","sourceType":"vendor","date":"2023-06-22","source":"https://inflection.ai/blog/inflection-1"}}},{"id":"instructgpt-175b","name":"InstructGPT 175B","provider":"OpenAI","openWeights":false,"release":"2022-01-27","aliases":["text-davinci-001","GPT-3","GPT-3 175B"],"page":null,"best":{"mmlu":{"score":43.9,"unit":"%","sourceType":"paper","date":"2022-01-27","source":"http://arxiv.org/abs/2112.11446"}}},{"id":"intellect-1","name":"INTELLECT-1","provider":"Prime Intellect","openWeights":null,"release":"2024-11-29","aliases":["INTELLECT-1-Instruct","INTELLECT-1-INSTRUCT"],"page":null,"best":{"mmlu":{"score":49.89,"unit":"%","sourceType":"paper","date":"2024-11-29","source":"https://arxiv.org/abs/2412.01152"}}},{"id":"intellect-3","name":"intellect-3","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1355.9,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"intern-s1","name":"Intern-S1","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":83.5,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"internlm-104b","name":"InternLM (104B)","provider":"Shanghai AI Lab (InternLM)","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu":{"score":67.2,"unit":"%","sourceType":"vendor","date":"","source":"https://static.aminer.cn/upload/pdf/127/1564/656/6481884993eaf7045294a0c4_0.pdf"}}},{"id":"internlm-7b","name":"internlm-7b","provider":"Shanghai AI Lab (InternLM)","openWeights":null,"release":"2023-07-05","aliases":["InternLM 7B"],"page":null,"best":{"mmlu":{"score":51,"unit":"%","sourceType":"paper","date":"2023-07-05","source":"https://arxiv.org/pdf/2309.16609"}}},{"id":"internlm-chat-20b","name":"internlm-chat-20b","provider":"Shanghai AI Lab (InternLM)","openWeights":null,"release":"2023-09-17","aliases":["InternLM-Chat 20B"],"page":null,"best":{"mmlu":{"score":57.4,"unit":"%","sourceType":"paper","date":"2023-09-17","source":"http://arxiv.org/abs/2403.04652"}}},{"id":"internlm2-5-1-8b-chat","name":"internlm2_5-1_8b-chat","provider":"Shanghai AI Lab (InternLM)","openWeights":true,"release":null,"aliases":["internlm/internlm2_5-1_8b-chat"],"page":null,"best":{"open-llm-leaderboard":{"score":14.75,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"internlm2-5-7b-chat","name":"internlm2_5-7b-chat","provider":"Shanghai AI Lab (InternLM)","openWeights":true,"release":null,"aliases":["internlm/internlm2_5-7b-chat"],"page":null,"best":{"open-llm-leaderboard":{"score":32.97,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"internlm2-1-8b","name":"internlm2-1_8b","provider":"Shanghai AI Lab (InternLM)","openWeights":true,"release":null,"aliases":["internlm/internlm2-1_8b"],"page":null,"best":{"open-llm-leaderboard":{"score":8.75,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"internlm2-7b","name":"internlm2-7b","provider":"Shanghai AI Lab (InternLM)","openWeights":true,"release":null,"aliases":["internlm/internlm2-7b"],"page":null,"best":{"open-llm-leaderboard":{"score":17.92,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"internlm2-chat-1-8b","name":"internlm2-chat-1_8b","provider":"Shanghai AI Lab (InternLM)","openWeights":true,"release":null,"aliases":["internlm/internlm2-chat-1_8b"],"page":null,"best":{"open-llm-leaderboard":{"score":10.64,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"internlm3-8b-instruct","name":"Internlm3-8B-Instruct","provider":"Shanghai AI Lab (InternLM)","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":57.6,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"internmath-20b-plus","name":"InternMath-20B-Plus","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":37.1,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"internmath-7b-plus","name":"InternMath-7B-Plus","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":33.5,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"internvl2-26b","name":"internvl2-26b","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-vision":{"score":1024.8,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"internvl2-4b","name":"internvl2-4b","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-vision":{"score":958.3,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"jamba-instruct","name":"Jamba Instruct","provider":"AI21 Labs","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu":{"score":65.9,"unit":"%","sourceType":"official","date":"","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"}}},{"id":"jamba-v0-1","name":"Jamba-v0.1","provider":"ai21labs","openWeights":true,"release":null,"aliases":["ai21labs/Jamba-v0.1"],"page":null,"best":{"open-llm-leaderboard":{"score":9.22,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"jiutian-57b","name":"JIUTIAN-57B","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"cmmlu":{"score":87.39,"unit":"%","sourceType":"official","date":"2024-12-06","source":"https://github.com/haonan-li/CMMLU#排行榜"}}},{"id":"jiutian","name":"Jiutian-大模型","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"cmmlu":{"score":88.59,"unit":"%","sourceType":"official","date":"2024-12-06","source":"https://github.com/haonan-li/CMMLU#排行榜"}}},{"id":"k2-5-1t-a32b","name":"K2.5-1T-A32B","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":87.1,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"kat-coder-pro-v1","name":"KAT-Coder-Pro-V1","provider":null,"openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-webdev":{"score":1255.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"}}},{"id":"kimi-k2-0905-preview","name":"kimi-k2-0905-preview","provider":"Moonshot AI","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1418.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"koala-13b","name":"koala-13b","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1070.9,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"laguna-m-1","name":"Laguna M.1","provider":"Poolside","openWeights":true,"release":"2026-04-28","aliases":["laguna-m.1"],"page":null,"best":{"lmarena-webdev":{"score":1348.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"}}},{"id":"laguna-xs-2","name":"Laguna XS.2","provider":"Poolside","openWeights":true,"release":"2026-04-28","aliases":["laguna-xs.2"],"page":null,"best":{"lmarena-webdev":{"score":1302.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"}}},{"id":"ling-flash-2-0","name":"ling-flash-2.0","provider":"ant-group","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1343.6,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"lingzhi-72b-chat","name":"Lingzhi-72B-chat","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"cmmlu":{"score":90.26,"unit":"%","sourceType":"official","date":"2024-12-06","source":"https://github.com/haonan-li/CMMLU#排行榜"}}},{"id":"llada","name":"LLaDA","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":37,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"llama-2-34b","name":"Llama 2-34B","provider":"Meta","openWeights":false,"release":"2023-07-18","aliases":["Llama-2-34b","LLAMA 2 34B","LLaMA 2 34B","LLaMA-2 34B"],"page":null,"best":{"mmlu":{"score":62.6,"unit":"%","sourceType":"paper","date":"2023-07-18","source":"http://arxiv.org/abs/2307.09288"}}},{"id":"llama-3-2-11b","name":"Llama 3.2 11B","provider":"Meta","openWeights":true,"release":"2024-09-24","aliases":["Llama-3.2-11B-Vision-Instruct","Llama 3.2 Vision Instruct Turbo (11B)"],"page":null,"best":{"mmlu":{"score":56.5,"unit":"%","sourceType":"official","date":"2024-09-24","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"}}},{"id":"llama-2-13b-chat-hf","name":"Llama-2-13b-chat-hf","provider":"Meta","openWeights":true,"release":null,"aliases":["meta-llama/Llama-2-13b-chat-hf"],"page":null,"best":{"open-llm-leaderboard":{"score":11.13,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"llama-2-13b-hf","name":"Llama-2-13b-hf","provider":"Meta","openWeights":true,"release":null,"aliases":["meta-llama/Llama-2-13b-hf"],"page":null,"best":{"open-llm-leaderboard":{"score":11.07,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"llama-2-7b-chat-hf","name":"Llama-2-7b-chat-hf","provider":"Meta","openWeights":true,"release":null,"aliases":["meta-llama/Llama-2-7b-chat-hf"],"page":null,"best":{"open-llm-leaderboard":{"score":9.61,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"llama-2-7b-hf","name":"Llama-2-7b-hf","provider":"Meta","openWeights":true,"release":null,"aliases":["meta-llama/Llama-2-7b-hf"],"page":null,"best":{"open-llm-leaderboard":{"score":8.81,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"llama-3-8b-sfr-iterative-dpo-r","name":"LLaMA-3-8B-SFR-Iterative-DPO-R","provider":"Salesforce","openWeights":true,"release":null,"aliases":["Salesforce/LLaMA-3-8B-SFR-Iterative-DPO-R"],"page":null,"best":{"open-llm-leaderboard":{"score":18.53,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"llama-3-1-405b-instruct-bf16","name":"llama-3.1-405b-instruct-bf16","provider":"Meta","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1335.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"llama-3-1-405b-instruct-fp8","name":"llama-3.1-405b-instruct-fp8","provider":"Meta","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1333.6,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"llama-3-1-minitron-4b-depth-base","name":"Llama-3.1-Minitron-4B-Depth-Base","provider":"NVIDIA","openWeights":true,"release":null,"aliases":["nvidia/Llama-3.1-Minitron-4B-Depth-Base"],"page":null,"best":{"open-llm-leaderboard":{"score":11.66,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"llama-3-1-nemotron-51b-instruct","name":"llama-3.1-nemotron-51b-instruct","provider":"NVIDIA","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1286.6,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"llama-3-1-nemotron-70b-instruct","name":"Llama-3.1-Nemotron-70B-Instruct","provider":"NVIDIA","openWeights":true,"release":"2024-12-18","aliases":["llama-3.1-nemotron-70b-instruct"],"page":null,"best":{"lmarena-text":{"score":1298.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"llama-3-1-tulu-3-70b-sft","name":"Llama-3.1-Tulu-3-70B-SFT","provider":"Ai2","openWeights":true,"release":null,"aliases":["allenai/Llama-3.1-Tulu-3-70B-SFT"],"page":null,"best":{"open-llm-leaderboard":{"score":38.85,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"llama-3-1-tulu-3-8b-dpo","name":"Llama-3.1-Tulu-3-8B-DPO","provider":"Ai2","openWeights":true,"release":null,"aliases":["allenai/Llama-3.1-Tulu-3-8B-DPO"],"page":null,"best":{"open-llm-leaderboard":{"score":26.46,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"llama-3-1-tulu-3-8b-rm","name":"Llama-3.1-Tulu-3-8B-RM","provider":"Ai2","openWeights":true,"release":null,"aliases":["allenai/Llama-3.1-Tulu-3-8B-RM"],"page":null,"best":{"open-llm-leaderboard":{"score":4.24,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"llama-3-1-tulu-3-8b-sft","name":"Llama-3.1-Tulu-3-8B-SFT","provider":"Ai2","openWeights":true,"release":null,"aliases":["allenai/Llama-3.1-Tulu-3-8B-SFT"],"page":null,"best":{"open-llm-leaderboard":{"score":22.6,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"llama-3-2-vision-11b-instruct","name":"llama-3.2-vision-11b-instruct","provider":"Meta","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-vision":{"score":992.7,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"llama-3-2-vision-90b-instruct","name":"llama-3.2-vision-90b-instruct","provider":"Meta","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-vision":{"score":1032.3,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"llama-3-3-nemotron-49b-super-v1","name":"llama-3.3-nemotron-49b-super-v1","provider":"NVIDIA","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1327.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"llama-33b","name":"LLaMA-33B","provider":"Meta","openWeights":true,"release":"2023-02-24","aliases":["LLAMA 1 33B","LLaMA 1 33B    ","LLaMA 33B"],"page":null,"best":{"mmlu":{"score":57.8,"unit":"%","sourceType":"paper","date":"2023-02-24","source":"http://arxiv.org/abs/2307.09288"}}},{"id":"llama-4-maverick-instruct","name":"llama-4-maverick-instruct","provider":"Meta","openWeights":null,"release":null,"aliases":["Llama 4 Maverick Instruct"],"page":null,"best":{"swe-bench-verified":{"score":21.04,"unit":"%","sourceType":"official","date":"2025-07-20","source":"https://www.swebench.com/#verified"}}},{"id":"llama-4-scout-instruct","name":"llama-4-scout-instruct","provider":"Meta","openWeights":null,"release":null,"aliases":["Llama 4 Scout Instruct"],"page":null,"best":{"swe-bench-verified":{"score":9.06,"unit":"%","sourceType":"official","date":"2025-07-20","source":"https://www.swebench.com/#verified"}}},{"id":"llama-7b","name":"LLaMA-7B","provider":"Meta","openWeights":true,"release":"2023-02-24","aliases":["LLAMA 1 7B","LLaMA 7B","Llama-7B"],"page":null,"best":{"mmlu":{"score":35.2,"unit":"%","sourceType":"paper","date":"2023-02-24","source":"http://arxiv.org/abs/2309.05463"}}},{"id":"llama2-70b-steerlm-chat","name":"llama2-70b-steerlm-chat","provider":"NVIDIA","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1154.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"llama3-70b-instruct","name":"Llama3-70B-instruct","provider":"Meta","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":72,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"llama3-8b-base","name":"Llama3-8B-base","provider":"Meta","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":29.3,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"llama3-8b-instruct","name":"Llama3-8B-instruct","provider":"Meta","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":56.7,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"llama3-smaug-8b","name":"Llama3-Smaug-8B","provider":"Meta","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":36.93,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"llama3-swe-rl-70b","name":"Llama3-SWE-RL-70B","provider":"Meta","openWeights":null,"release":null,"aliases":["SWE-RL (Llama3-SWE-RL-70B + Agentless Mini) (20250226)"],"page":null,"best":{"swe-bench-verified":{"score":41.2,"unit":"%","sourceType":"official","date":"2025-02-26","source":"https://www.swebench.com/#verified"}}},{"id":"llama3-1-8b-instruct","name":"Llama3.1-8B-instruct","provider":"Meta","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":62.8,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"llama4-behemoth","name":"Llama4-Behemoth","provider":"Meta","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":82.8,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"llama4-maverick","name":"Llama4-Maverick","provider":"Meta","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":80.5,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"llama4-scout","name":"Llama4-Scout","provider":"Meta","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":74.3,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"llava-onevision-qwen2-72b-ov","name":"llava-onevision-qwen2-72b-ov","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-vision":{"score":978.3,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"llava-v1-6-34b","name":"llava-v1.6-34b","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-vision":{"score":964.4,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"llemma-7b","name":"Llemma-7B","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":23.45,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"longcat-flash-chat-2602-exp","name":"longcat-flash-chat-2602-exp","provider":"Meituan","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1436.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"magicoder-s-cl-7b","name":"Magicoder-S-CL-7B","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":67.7,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"magicoder-s-ds-6-7b","name":"Magicoder-S-DS-6.7B","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":71.3,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"magistral-medium-1-1","name":"Magistral Medium 1.1","provider":"Mistral AI","openWeights":false,"release":"2025-06-10","aliases":["magistral-medium-2506"],"page":null,"best":{"lmarena-text":{"score":1304.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"magnum-72b-v1","name":"magnum-72b-v1","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":63.93,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"mammoth2-7b-plus","name":"MAmmoTH2-7B-Plus","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":40.85,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"mammoth2-8b-plus","name":"MAmmoTH2-8B-Plus","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":43.35,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"mammoth2-8x7b-plus","name":"MAmmoTH2-8x7B-Plus","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":50.4,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"mathstral-7b-v0-1","name":"Mathstral-7B-v0.1","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":42,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"mcts-refine-7b","name":"MCTS-Refine-7B","provider":null,"openWeights":null,"release":null,"aliases":["MCTS Refine 7B"],"page":null,"best":{"swe-bench-verified":{"score":23.2,"unit":"%","sourceType":"official","date":"2025-06-27","source":"https://www.swebench.com/#verified"}}},{"id":"mercury","name":"mercury","provider":"inception-ai","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1305.9,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"mimo-7b-base","name":"Mimo-7B-base","provider":"Xiaomi","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":41.9,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"mimo-7b-rl","name":"Mimo-7B-RL","provider":"Xiaomi","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":58.6,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"minicpm-s-1b-sft-llama-format","name":"MiniCPM-S-1B-sft-llama-format","provider":"openbmb","openWeights":true,"release":null,"aliases":["openbmb/MiniCPM-S-1B-sft-llama-format"],"page":null,"best":{"open-llm-leaderboard":{"score":9,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"minicpm-v-2-6","name":"minicpm-v-2_6","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-vision":{"score":962.7,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"minicpm3-4b","name":"MiniCPM3-4B-FC","provider":"openbmb","openWeights":true,"release":null,"aliases":["MiniCPM3-4B-FC (FC)","MiniCPM3-4B (Prompt)"],"page":null,"best":{"bfcl":{"score":25.55,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"minimax-text-01","name":"MiniMax-Text-01","provider":"MiniMax","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":75.7,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"minitron-4b-base","name":"Minitron-4B-Base","provider":"NVIDIA","openWeights":true,"release":null,"aliases":["nvidia/Minitron-4B-Base"],"page":null,"best":{"open-llm-leaderboard":{"score":11.98,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"minitron-8b-base","name":"Minitron-8B-Base","provider":"NVIDIA","openWeights":true,"release":null,"aliases":["nvidia/Minitron-8B-Base"],"page":null,"best":{"open-llm-leaderboard":{"score":14.22,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"mistral-large-mar-2024","name":"Mistral Large (Mar 2024)","provider":"Mistral AI","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":62.2,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"mistral-nemo-2402","name":"Mistral NeMo (2402)","provider":"Mistral AI","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu":{"score":65.3,"unit":"%","sourceType":"official","date":"","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"}}},{"id":"mistral-3-1-small","name":"Mistral-3.1-Small","provider":"Mistral AI","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":66.8,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"mistral-7b","name":"Mistral-7B","provider":"Mistral AI","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":23.8,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"mistral-7b-instruct","name":"mistral-7b-instruct","provider":"Mistral AI","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1110.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"mistral-codealpaca-7b","name":"Mistral-codealpaca-7B","provider":"Mistral AI","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":42.1,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"mistral","name":"mistral-medium","provider":"Mistral AI","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1222.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"mistral-nemo-minitron-8b-base","name":"Mistral-NeMo-Minitron-8B-Base","provider":"NVIDIA","openWeights":true,"release":null,"aliases":["nvidia/Mistral-NeMo-Minitron-8B-Base"],"page":null,"best":{"open-llm-leaderboard":{"score":17.7,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"mistral-nemo-minitron-8b-instruct","name":"Mistral-NeMo-Minitron-8B-Instruct","provider":"NVIDIA","openWeights":true,"release":null,"aliases":["nvidia/Mistral-NeMo-Minitron-8B-Instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":23.57,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"mistral-small-2402","name":"mistral-small-2402","provider":"Mistral AI","openWeights":null,"release":"2024-02-26","aliases":["Mistral Small (2402)"],"page":null,"best":{"mmlu":{"score":68.7,"unit":"%","sourceType":"official","date":"2024-02-26","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"}}},{"id":"mistral-small-24b-base-2501","name":"Mistral-Small-24B-Base-2501","provider":"Mistral AI","openWeights":true,"release":null,"aliases":["mistralai/Mistral-Small-24B-Base-2501"],"page":null,"best":{"open-llm-leaderboard":{"score":27.2,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"mistral-small-24b-instruct-2501","name":"mistral-small-24b-instruct-2501","provider":"Mistral AI","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1274.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"mistral-small-base","name":"Mistral-Small-base","provider":"Mistral AI","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":54.4,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"mistral-small-instruct","name":"Mistral-Small-instruct","provider":"Mistral AI","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":66.3,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"mistralhermes-codepro-7b-v1","name":"MistralHermes-CodePro-7B-v1","provider":"Mistral AI","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":42.1,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"mixtral-8x7b-32k-seqlen","name":"Mixtral (8x7B 32K seqlen)","provider":"Mistral AI","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu":{"score":71.7,"unit":"%","sourceType":"official","date":"","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"}}},{"id":"molmo-72b-0924","name":"molmo-72b-0924","provider":"Ai2","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-vision":{"score":1044.9,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"molmo-7b-d-0924","name":"molmo-7b-d-0924","provider":"Ai2","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-vision":{"score":993.8,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"moonshotai-kimi-k2-instruct","name":"Moonshotai-Kimi-K2-Instruct","provider":"Moonshot AI","openWeights":true,"release":null,"aliases":["Moonshotai-Kimi-K2-Instruct (FC)"],"page":null,"best":{"bfcl":{"score":59.06,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"moss","name":"MOSS","provider":"Fudan (OpenMOSS)","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"c-eval":{"score":31.1,"unit":"%","sourceType":"official","date":"2023-05-15","source":"https://github.com/hkust-nlp/ceval#leaderboard"}}},{"id":"mpt-30b","name":"MPT-30B","provider":"MosaicML","openWeights":true,"release":"2023-06-22","aliases":["mpt-30b","MPT 30B"],"page":null,"best":{"mmlu":{"score":47.9,"unit":"%","sourceType":"paper","date":"2023-06-22","source":"https://arxiv.org/pdf/2309.16609"}}},{"id":"mpt-30b-chat","name":"mpt-30b-chat","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1150.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"mpt-7b-chat","name":"mpt-7b-chat","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1063.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"mt5-base","name":"mt5-base","provider":"Google","openWeights":true,"release":null,"aliases":["google/mt5-base"],"page":null,"best":{"open-llm-leaderboard":{"score":3.72,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"mt5-small","name":"mt5-small","provider":"Google","openWeights":true,"release":null,"aliases":["google/mt5-small"],"page":null,"best":{"open-llm-leaderboard":{"score":4.26,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"mt5-xl","name":"mt5-xl","provider":"Google","openWeights":true,"release":null,"aliases":["google/mt5-xl"],"page":null,"best":{"open-llm-leaderboard":{"score":5.19,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"mt5-xxl","name":"mt5-xxl","provider":"Google","openWeights":true,"release":null,"aliases":["google/mt5-xxl"],"page":null,"best":{"open-llm-leaderboard":{"score":5.1,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"muse-wonder","name":"Muse Wonder","provider":"Meta","openWeights":false,"release":"2026-10-12","aliases":["muse-wonder-1.0_max","Muse Wonder (max)"],"page":null,"best":{"aime":{"score":99.44,"unit":"%","sourceType":"independent","date":"2026-10-12","source":"https://epoch.ai/benchmarks"}}},{"id":"nanbeige3-5-pro","name":"Nanbeige3.5-Pro-Thinking","provider":"Nanbeige","openWeights":true,"release":null,"aliases":["Nanbeige3.5-Pro-Thinking (FC)"],"page":null,"best":{"bfcl":{"score":47.68,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"nanbeige4-3b-thinking-2511","name":"Nanbeige4-3B-Thinking-2511","provider":"Nanbeige","openWeights":true,"release":null,"aliases":["Nanbeige4-3B-Thinking-2511 (FC)"],"page":null,"best":{"bfcl":{"score":51.4,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"nemotron-3-nano-30b-a3b-base","name":"Nemotron-3-Nano-30B-A3B-Base","provider":"NVIDIA","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":65.1,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"nemotron-3-nano-30b-a3b-bf16","name":"Nemotron-3-Nano-30B-A3B(BF16)","provider":"NVIDIA","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":78.3,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"nemotron-3-nano-30b-a3b-fp8","name":"Nemotron-3-Nano-30B-A3B(FP8)","provider":"NVIDIA","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":78.1,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"nemotron-4-15b","name":"Nemotron-4 15B","provider":"NVIDIA","openWeights":false,"release":"2024-02-26","aliases":[],"page":null,"best":{"mmlu":{"score":58.7,"unit":"%","sourceType":"paper","date":"2024-02-26","source":"http://arxiv.org/abs/2402.16819"}}},{"id":"nemotron-4-340b","name":"nemotron-4-340b-instruct","provider":"NVIDIA","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1277.2,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"nemotron-h-56b-base","name":"Nemotron-H-56B-Base","provider":"NVIDIA","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":60.5,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"nemotron-h-8b-base","name":"Nemotron-H-8B-Base","provider":"NVIDIA","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":44,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"nemotron-mini-4b-instruct","name":"Nemotron-Mini-4B-Instruct","provider":"NVIDIA","openWeights":true,"release":null,"aliases":["nvidia/Nemotron-Mini-4B-Instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":18.36,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"nemotron-orchestrator-8b","name":"Nemotron-Orchestrator-8B","provider":"NVIDIA","openWeights":null,"release":"2025-11-26","aliases":[],"page":null,"best":{"tau2-bench":{"score":84.2,"unit":"%","sourceType":"vendor","date":"2025-09-15","source":"https://arxiv.org/abs/2511.21689"}}},{"id":"neo-7b","name":"Neo-7B","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":25.85,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"neo-7b-instruct","name":"Neo-7B-Instruct","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":28.74,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"nexusraven-v2-13b","name":"NexusRaven-V2-13B","provider":"Nexusflow","openWeights":true,"release":null,"aliases":["Nexusflow/NexusRaven-V2-13B"],"page":null,"best":{"open-llm-leaderboard":{"score":8.49,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"nous-hermes-2-mistral-7b-dpo","name":"Nous-Hermes-2-Mistral-7B-DPO","provider":"NousResearch","openWeights":true,"release":null,"aliases":["NousResearch/Nous-Hermes-2-Mistral-7B-DPO"],"page":null,"best":{"open-llm-leaderboard":{"score":21.1,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"nous-hermes-2-mixtral-8x7b-sft","name":"Nous-Hermes-2-Mixtral-8x7B-SFT","provider":"NousResearch","openWeights":true,"release":null,"aliases":["NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT"],"page":null,"best":{"open-llm-leaderboard":{"score":21.84,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"nous-hermes-2-solar-10-7b","name":"Nous-Hermes-2-SOLAR-10.7B","provider":"NousResearch","openWeights":true,"release":null,"aliases":["NousResearch/Nous-Hermes-2-SOLAR-10.7B"],"page":null,"best":{"open-llm-leaderboard":{"score":23.41,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"nous-hermes-llama-2-7b","name":"Nous-Hermes-llama-2-7b","provider":"NousResearch","openWeights":true,"release":null,"aliases":["NousResearch/Nous-Hermes-llama-2-7b"],"page":null,"best":{"open-llm-leaderboard":{"score":9.32,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"nova-2-lite","name":"nova-2-lite","provider":"Amazon","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1334.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"nvidia-llama-3-3-nemotron-super-49b-v1-5","name":"nvidia-llama-3.3-nemotron-super-49b-v1.5","provider":"NVIDIA","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1343.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"nvidia-nemotron-3-nano-30b-a3b-bf16","name":"nvidia-nemotron-3-nano-30b-a3b-bf16","provider":"NVIDIA","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1313.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"nvidia-nemotron-3-super-120b-a12b","name":"nvidia-nemotron-3-super-120b-a12b","provider":"NVIDIA","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1360.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"nvidia-nemotron-3-ultra-550b-a55b-nvfp4","name":"nvidia-nemotron-3-ultra-550b-a55b-nvfp4","provider":"NVIDIA","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1426.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"nvidia-nemotron-3-5-lightning-30b-a3b-nvfp4","name":"nvidia-nemotron-3.5-lightning-30b-a3b-nvfp4","provider":"NVIDIA","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1349.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"nvila-internal-15b-v1","name":"nvila-internal-15b-v1","provider":"NVIDIA","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-vision":{"score":985.4,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"seed-oss-36b-base-w-o-syn","name":"o syn.)","provider":"ByteDance","openWeights":null,"release":null,"aliases":["Seed-OSS-36B-Base(w/o syn.)"],"page":null,"best":{"mmlu-pro":{"score":60.4,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"o1-mini-sept-2024","name":"O1 Mini (Sept 2024)","provider":"OpenAI","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":89,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"o1-preview-sept-2024","name":"O1 Preview (Sept 2024)","provider":"OpenAI","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":89,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"o1-pro","name":"o1-pro","provider":"OpenAI","openWeights":false,"release":"2025-03-19","aliases":["o1-pro-2025-03-19","o1 Pro"],"page":null,"best":{"hle":{"score":8.12,"unit":"%","sourceType":"compiled","date":"2025-03-19","source":"https://epoch.ai/benchmarks"}}},{"id":"oasst-pythia-12b","name":"oasst-pythia-12b","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1023.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"olmo-7b","name":"OLMo (7B)","provider":"Ai2","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu":{"score":29.5,"unit":"%","sourceType":"official","date":"","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"}}},{"id":"olmo-1-7-7b","name":"OLMo 1.7 (7B)","provider":"Ai2","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu":{"score":53.8,"unit":"%","sourceType":"official","date":"","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"}}},{"id":"olmo-1-7-7b-hf","name":"OLMo-1.7-7B-hf","provider":"Ai2","openWeights":true,"release":null,"aliases":["allenai/OLMo-1.7-7B-hf"],"page":null,"best":{"open-llm-leaderboard":{"score":3.8,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"olmo-1b-hf","name":"OLMo-1B-hf","provider":"Ai2","openWeights":true,"release":null,"aliases":["allenai/OLMo-1B-hf"],"page":null,"best":{"open-llm-leaderboard":{"score":6.63,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"olmo-2-0325-32b-instruct","name":"olmo-2-0325-32b-instruct","provider":"Ai2","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1251.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"olmo-2-1124-7b-instruct","name":"OLMo-2-1124-7B-Instruct","provider":"Ai2","openWeights":true,"release":null,"aliases":["allenai/OLMo-2-1124-7B-Instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":21.79,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"olmo-3-32b-think","name":"olmo-3-32b-think","provider":"Ai2","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1306.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"olmo-3-1-32b-instruct","name":"olmo-3.1-32b-instruct","provider":"Ai2","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1329.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"olmo-3-1-32b-think","name":"olmo-3.1-32b-think","provider":"Ai2","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1286.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"olmo-7b-hf","name":"OLMo-7B-hf","provider":"Ai2","openWeights":true,"release":null,"aliases":["allenai/OLMo-7B-hf"],"page":null,"best":{"open-llm-leaderboard":{"score":6.86,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"olmo-7b-instruct","name":"olmo-7b-instruct","provider":"Ai2","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1073.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"olmo-7b-instruct-hf","name":"OLMo-7B-Instruct-hf","provider":"Ai2","openWeights":true,"release":null,"aliases":["allenai/OLMo-7B-Instruct-hf"],"page":null,"best":{"open-llm-leaderboard":{"score":10.85,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"olmoe-1b-7b-0125-instruct","name":"OLMoE-1B-7B-0125-Instruct","provider":"Ai2","openWeights":true,"release":null,"aliases":["allenai/OLMoE-1B-7B-0125-Instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":17.51,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"olmoe-1b-7b-0924","name":"OLMoE-1B-7B-0924","provider":"Ai2","openWeights":true,"release":null,"aliases":["allenai/OLMoE-1B-7B-0924"],"page":null,"best":{"open-llm-leaderboard":{"score":7.27,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"olmoe-1b-7b-0924-instruct","name":"OLMoE-1B-7B-0924-Instruct","provider":"Ai2","openWeights":true,"release":null,"aliases":["allenai/OLMoE-1B-7B-0924-Instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":13.7,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"open-llama-7b","name":"open_llama_7b","provider":null,"openWeights":null,"release":"2023-06-07","aliases":["OpenLLaMA-7B"],"page":null,"best":{"mmlu":{"score":29.9,"unit":"%","sourceType":"paper","date":"2023-06-07","source":"http://arxiv.org/abs/2309.03450"}}},{"id":"openchat-3-5","name":"openchat-3.5","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1183,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"openchat-3-5-0106","name":"openchat-3.5-0106","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1182.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"openchat-3-5-7b-0106","name":"OpenChat-3.5-7B-0106","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":67.7,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"openchat-3-5-8b","name":"OpenChat-3.5-8B","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":37.24,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"opencodeinterpreter-ds-33b","name":"OpenCodeInterpreter-DS-33B","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":73.8,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"opencodeinterpreter-ds-6-7b","name":"OpenCodeInterpreter-DS-6.7B","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":72,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"opencoder-8b-instruct","name":"OpenCoder-8B-Instruct","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":77.4,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"opencodereasoning-nemotron-1-1-32b","name":"OpenCodeReasoning-Nemotron-1.1-32B","provider":"NVIDIA","openWeights":true,"release":null,"aliases":["nvidia/OpenCodeReasoning-Nemotron-1.1-32B"],"page":null,"best":{"livecodebench":{"score":62.4,"unit":"%","sourceType":"official","date":"2025-04-07","source":"https://livecodebench.github.io/leaderboard.html"}}},{"id":"openhermes-13b","name":"OpenHermes-13B","provider":"teknium","openWeights":true,"release":null,"aliases":["teknium/OpenHermes-13B"],"page":null,"best":{"open-llm-leaderboard":{"score":12.18,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"openhermes-2-mistral-7b","name":"OpenHermes-2-Mistral-7B","provider":"teknium","openWeights":true,"release":null,"aliases":["teknium/OpenHermes-2-Mistral-7B"],"page":null,"best":{"open-llm-leaderboard":{"score":21.44,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"openhermes-2-5-code-290k-13b","name":"OpenHermes-2.5-Code-290k-13B","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":48.8,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"openhermes-7b","name":"OpenHermes-7B","provider":"teknium","openWeights":true,"release":null,"aliases":["teknium/OpenHermes-7B"],"page":null,"best":{"open-llm-leaderboard":{"score":9.57,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"openmath2-llama3-1-8b","name":"OpenMath2-Llama3.1-8B","provider":"NVIDIA","openWeights":true,"release":null,"aliases":["nvidia/OpenMath2-Llama3.1-8B"],"page":null,"best":{"open-llm-leaderboard":{"score":12.75,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"openreasoning-nemotron-32b","name":"OpenReasoning-Nemotron-32B","provider":"NVIDIA","openWeights":true,"release":null,"aliases":["nvidia/OpenReasoning-Nemotron-32B"],"page":null,"best":{"livecodebench":{"score":66.6,"unit":"%","sourceType":"official","date":"2025-04-07","source":"https://livecodebench.github.io/leaderboard.html"}}},{"id":"opt-13b","name":"opt-13b","provider":null,"openWeights":null,"release":"2022-05-11","aliases":["OPT-13B"],"page":null,"best":{"mmlu":{"score":25.1,"unit":"%","sourceType":"paper","date":"2022-05-11","source":"http://arxiv.org/abs/2309.03450"}}},{"id":"orca-2-13b","name":"Orca-2-13b","provider":"Microsoft","openWeights":true,"release":null,"aliases":["microsoft/Orca-2-13b"],"page":null,"best":{"open-llm-leaderboard":{"score":18.5,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"orca-2-7b","name":"Orca-2-7b","provider":"Microsoft","openWeights":true,"release":null,"aliases":["microsoft/Orca-2-7b"],"page":null,"best":{"open-llm-leaderboard":{"score":14.4,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"palm-540b","name":"PaLM (540B)","provider":"Google Research","openWeights":false,"release":"2022-04-04","aliases":["PaLM 540B"],"page":null,"best":{"mmlu":{"score":69.3,"unit":"%","sourceType":"paper","date":"2022-04-04","source":"http://arxiv.org/abs/2302.13971"}}},{"id":"palm-62b","name":"PaLM 62B","provider":"Google","openWeights":null,"release":"2022-04-04","aliases":[],"page":null,"best":{"mmlu":{"score":53.7,"unit":"%","sourceType":"paper","date":"2022-04-04","source":"http://arxiv.org/abs/2302.13971"}}},{"id":"palm-8b","name":"PaLM 8B","provider":"Google","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu":{"score":25.4,"unit":"%","sourceType":"paper","date":"","source":"http://arxiv.org/abs/2302.13971"}}},{"id":"palm-2","name":"palm-2","provider":"Google","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1139.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"palm-2-bison","name":"PaLM-2 (Bison)","provider":"Google","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu":{"score":69.2,"unit":"%","sourceType":"official","date":"","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"}}},{"id":"palm-2-unicorn","name":"PaLM-2 (Unicorn)","provider":"Google","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu":{"score":78.6,"unit":"%","sourceType":"official","date":"","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"}}},{"id":"palmyra-x-v2-33b","name":"Palmyra X V2 (33B)","provider":"Google","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu":{"score":62.1,"unit":"%","sourceType":"official","date":"","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"}}},{"id":"palmyra-x-v3-72b","name":"Palmyra X V3 (72B)","provider":"Google","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu":{"score":78.6,"unit":"%","sourceType":"official","date":"","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"}}},{"id":"pci-transgpt","name":"PCI-TransGPT","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{}},{"id":"phi-1","name":"phi-1","provider":"Microsoft","openWeights":true,"release":null,"aliases":["microsoft/phi-1"],"page":null,"best":{"open-llm-leaderboard":{"score":5.57,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"phi-2-2-7b","name":"phi-2-2.7B","provider":"Microsoft","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":45.1,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"phi-3-7b","name":"Phi-3 (7B)","provider":"Microsoft","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu":{"score":75.7,"unit":"%","sourceType":"official","date":"","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"}}},{"id":"phi-3-mini-4k-instruct-june-2024","name":"phi-3-mini-4k-instruct-june-2024","provider":"Microsoft","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1143.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"phi-3-small-128k-instruct","name":"Phi-3-small-128k-instruct","provider":"Microsoft","openWeights":true,"release":null,"aliases":["microsoft/Phi-3-small-128k-instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":31.97,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"phi-3-vision-128k-instruct","name":"phi-3-vision-128k-instruct","provider":"Microsoft","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-vision":{"score":881.1,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"phi-3-5-moe","name":"Phi-3.5-MoE-instruct","provider":"Microsoft","openWeights":true,"release":null,"aliases":["microsoft/Phi-3.5-MoE-instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":36.88,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"phi-3-5-vision-instruct","name":"phi-3.5-vision-instruct","provider":"Microsoft","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-vision":{"score":919.5,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"phi-4-reasoning-plus","name":"Phi-4-reasoning-plus","provider":"Microsoft","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":76,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"phi3","name":"Phi3-medium-128k","provider":null,"openWeights":null,"release":null,"aliases":["Phi3-medium-4k"],"page":null,"best":{"mmlu-pro":{"score":51.91,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"phi3-mini","name":"Phi3-mini-128k","provider":null,"openWeights":null,"release":null,"aliases":["Phi3-mini-4k"],"page":null,"best":{"mmlu-pro":{"score":43.86,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"phi4-sft","name":"Phi4-sft","provider":null,"openWeights":null,"release":null,"aliases":["NewenAI/Phi4-sft"],"page":null,"best":{"mmlu-pro":{"score":57.7,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"phind-codellama-34b-v2","name":"Phind-CodeLlama-34B-v2","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":67.1,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"pixtral-large","name":"Pixtral Large","provider":"Mistral AI","openWeights":true,"release":"2024-11-18","aliases":["pixtral-large-2411"],"page":null,"best":{"lmarena-vision":{"score":1095.2,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"pixtral-12b","name":"pixtral-12b-2409","provider":"Mistral AI","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-vision":{"score":1025.2,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"polycoder-2-7b","name":"PolyCoder-2.7B","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":6.1,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"pythia-1-4b","name":"pythia-1.4b","provider":"EleutherAI","openWeights":true,"release":null,"aliases":["EleutherAI/pythia-1.4b"],"page":null,"best":{"open-llm-leaderboard":{"score":6.01,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"pythia-12b","name":"pythia-12b","provider":"EleutherAI","openWeights":true,"release":null,"aliases":["EleutherAI/pythia-12b"],"page":null,"best":{"open-llm-leaderboard":{"score":6.06,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"pythia-160m","name":"pythia-160m","provider":"EleutherAI","openWeights":true,"release":null,"aliases":["EleutherAI/pythia-160m"],"page":null,"best":{"open-llm-leaderboard":{"score":5.73,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"pythia-1b","name":"pythia-1b","provider":"EleutherAI","openWeights":true,"release":null,"aliases":["EleutherAI/pythia-1b"],"page":null,"best":{"open-llm-leaderboard":{"score":5.07,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"pythia-2-8b","name":"pythia-2.8b","provider":"EleutherAI","openWeights":true,"release":null,"aliases":["EleutherAI/pythia-2.8b"],"page":null,"best":{"open-llm-leaderboard":{"score":5.55,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"pythia-410m","name":"pythia-410m","provider":"EleutherAI","openWeights":true,"release":null,"aliases":["EleutherAI/pythia-410m"],"page":null,"best":{"open-llm-leaderboard":{"score":5.23,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"pythia-6-9b","name":"pythia-6.9b","provider":"EleutherAI","openWeights":true,"release":null,"aliases":["EleutherAI/pythia-6.9b"],"page":null,"best":{"open-llm-leaderboard":{"score":5.97,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"python-code-13b","name":"Python-Code-13B","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":30.5,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"qwen-2-5","name":"Qwen 2.5","provider":"Alibaba (Qwen)","openWeights":null,"release":null,"aliases":["SWE-agent-LM-32B","SWE-agent + SWE-agent-LM-32B","Qwen2.5 (7B + 72B)","SWE-Fixer (Qwen2.5-7b retriever + Qwen2.5-72b editor)","SWE-Fixer (Qwen2.5-7b retriever + Qwen2.5-72b editor) 20241128"],"page":null,"best":{"swe-bench-verified":{"score":40.2,"unit":"%","sourceType":"official","date":"2025-05-11","source":"https://www.swebench.com/#verified"}}},{"id":"qwen-1-8b","name":"Qwen-1_8B","provider":"Alibaba (Qwen)","openWeights":null,"release":"2023-11-30","aliases":["Qwen-1.8B","Qwen 1.8B"],"page":null,"best":{"mmlu":{"score":28.2,"unit":"%","sourceType":"paper","date":"2023-11-30","source":"https://arxiv.org/pdf/2309.16609"}}},{"id":"qwen-7b","name":"Qwen-7B","provider":"Alibaba (Qwen)","openWeights":true,"release":"2023-09-28","aliases":["Qwen 7B"],"page":null,"best":{"mmlu":{"score":45,"unit":"%","sourceType":"paper","date":"2023-09-28","source":"https://arxiv.org/pdf/2309.16609"}}},{"id":"qwen-max-0919","name":"qwen-max-0919","provider":"Alibaba (Qwen)","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1318.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"qwen-plus-0125","name":"qwen-plus-0125","provider":"Alibaba (Qwen)","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1345.9,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"qwen-vl-max-1119","name":"qwen-vl-max-1119","provider":"Alibaba (Qwen)","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-vision":{"score":1084.7,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"qwen-vl-max","name":"qwen-vl-max-2025-08-13","provider":"Alibaba (Qwen)","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-vision":{"score":1184.9,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"qwen1-5-chat-110b","name":"Qwen1.5 Chat (110B)","provider":"Alibaba (Qwen)","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu":{"score":76.8,"unit":"%","sourceType":"official","date":"","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"}}},{"id":"qwen1-5-0-5b","name":"Qwen1.5-0.5B","provider":"Alibaba (Qwen)","openWeights":true,"release":null,"aliases":["Qwen/Qwen1.5-0.5B"],"page":null,"best":{"open-llm-leaderboard":{"score":5.35,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"qwen1-5-0-5b-chat","name":"Qwen1.5-0.5B-Chat","provider":"Alibaba (Qwen)","openWeights":true,"release":null,"aliases":["Qwen/Qwen1.5-0.5B-Chat"],"page":null,"best":{"open-llm-leaderboard":{"score":5.68,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"qwen1-5-1-8b","name":"Qwen1.5-1.8B","provider":"Alibaba (Qwen)","openWeights":true,"release":null,"aliases":["Qwen/Qwen1.5-1.8B"],"page":null,"best":{"open-llm-leaderboard":{"score":9.27,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"qwen1-5-1-8b-chat","name":"Qwen1.5-1.8B-Chat","provider":"Alibaba (Qwen)","openWeights":true,"release":null,"aliases":["Qwen/Qwen1.5-1.8B-Chat"],"page":null,"best":{"open-llm-leaderboard":{"score":9.26,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"qwen1-5-4b","name":"Qwen1.5-4B","provider":"Alibaba (Qwen)","openWeights":true,"release":null,"aliases":["Qwen/Qwen1.5-4B"],"page":null,"best":{"open-llm-leaderboard":{"score":11.77,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"qwen1-5-moe-a2-7b","name":"Qwen1.5-MoE-A2.7B","provider":"Alibaba (Qwen)","openWeights":true,"release":null,"aliases":["Qwen/Qwen1.5-MoE-A2.7B"],"page":null,"best":{"open-llm-leaderboard":{"score":13.95,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"qwen1-5-moe-a2-7b-chat","name":"Qwen1.5-MoE-A2.7B-Chat","provider":"Alibaba (Qwen)","openWeights":true,"release":null,"aliases":["Qwen/Qwen1.5-MoE-A2.7B-Chat"],"page":null,"best":{"open-llm-leaderboard":{"score":15.88,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"qwen2-57b-a14b","name":"Qwen2-57B-A14B-Instruct","provider":"Alibaba (Qwen)","openWeights":true,"release":null,"aliases":["Qwen/Qwen2-57B-A14B-Instruct","Qwen/Qwen2-57B-A14B"],"page":null,"best":{"open-llm-leaderboard":{"score":33.02,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"qwen2-72b-chat","name":"Qwen2-72B-Chat","provider":"Alibaba (Qwen)","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":64.38,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"qwen2-math-72b-instruct","name":"Qwen2-Math-72B-Instruct","provider":"Alibaba (Qwen)","openWeights":true,"release":null,"aliases":["Qwen/Qwen2-Math-72B-Instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":38.02,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"qwen2-math-7b","name":"Qwen2-Math-7B","provider":"Alibaba (Qwen)","openWeights":true,"release":null,"aliases":["Qwen/Qwen2-Math-7B"],"page":null,"best":{"open-llm-leaderboard":{"score":12.02,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"qwen2-vl-72b","name":"qwen2-vl-72b","provider":"Alibaba (Qwen)","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-vision":{"score":1084.8,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"qwen2-vl-72b-instruct","name":"Qwen2-VL-72B-Instruct","provider":"Alibaba (Qwen)","openWeights":true,"release":null,"aliases":["Qwen/Qwen2-VL-72B-Instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":39.54,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"qwen2-5-0-5b-instruct","name":"Qwen2.5-0.5B-Instruct","provider":"Alibaba (Qwen)","openWeights":true,"release":null,"aliases":["Qwen/Qwen2.5-0.5B-Instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":10.11,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"qwen2-5-14b-instruct-1m","name":"Qwen2.5-14B-Instruct-1M","provider":"Alibaba (Qwen)","openWeights":true,"release":null,"aliases":["Qwen/Qwen2.5-14B-Instruct-1M"],"page":null,"best":{"open-llm-leaderboard":{"score":41.56,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"qwen2-5-7b-instruct-1m","name":"Qwen2.5-7B-Instruct-1M","provider":"Alibaba (Qwen)","openWeights":true,"release":null,"aliases":["Qwen/Qwen2.5-7B-Instruct-1M"],"page":null,"best":{"open-llm-leaderboard":{"score":32.76,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"qwen2-5-coder-1-5b","name":"Qwen2.5-Coder (1.5B)","provider":"Alibaba (Qwen)","openWeights":true,"release":"2024-09-18","aliases":["Qwen2.5-Coder-1.5B"],"page":null,"best":{"mmlu":{"score":53.6,"unit":"%","sourceType":"paper","date":"2024-09-18","source":"http://arxiv.org/abs/2409.12186"}}},{"id":"qwen2-5-coder-0-5b","name":"Qwen2.5-Coder-0.5B","provider":"Alibaba (Qwen)","openWeights":null,"release":"2024-09-18","aliases":[],"page":null,"best":{"mmlu":{"score":42,"unit":"%","sourceType":"paper","date":"2024-09-18","source":"http://arxiv.org/abs/2409.12186"}}},{"id":"qwen2-5-coder-14b-instruct","name":"Qwen2.5-Coder-14B-Instruct","provider":"Alibaba (Qwen)","openWeights":true,"release":null,"aliases":["Qwen/Qwen2.5-Coder-14B-Instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":32.12,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"qwen2-5-math-1-5b-instruct","name":"Qwen2.5-Math-1.5B-Instruct","provider":"Alibaba (Qwen)","openWeights":true,"release":null,"aliases":["Qwen/Qwen2.5-Math-1.5B-Instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":12.02,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"qwen2-5-math-72b-instruct","name":"Qwen2.5-Math-72B-Instruct","provider":"Alibaba (Qwen)","openWeights":true,"release":null,"aliases":["Qwen/Qwen2.5-Math-72B-Instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":36.82,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"qwen2-5-math-7b","name":"Qwen2.5-Math-7B","provider":"Alibaba (Qwen)","openWeights":true,"release":null,"aliases":["Qwen/Qwen2.5-Math-7B"],"page":null,"best":{"open-llm-leaderboard":{"score":17.84,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"qwen2-5-math-7b-instruct","name":"Qwen2.5-Math-7B-Instruct","provider":"Alibaba (Qwen)","openWeights":true,"release":null,"aliases":["Qwen/Qwen2.5-Math-7B-Instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":21.77,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"qwen2-5-plus-1127","name":"qwen2.5-plus-1127","provider":"Alibaba (Qwen)","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1314.6,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"qwen2-5-turbo","name":"Qwen2.5-Turbo","provider":"Alibaba (Qwen)","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":55.6,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"qwen2-5-vl-32b-instruct","name":"qwen2.5-vl-32b-instruct","provider":"Alibaba (Qwen)","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-vision":{"score":1118.6,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"qwen3-0-6b","name":"Qwen3-0.6B","provider":"Alibaba (Qwen)","openWeights":true,"release":null,"aliases":["Qwen3-0.6B (FC)","Qwen3-0.6B (Prompt)"],"page":null,"best":{"bfcl":{"score":23.93,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"qwen3-235b-a22b-no","name":"qwen3-235b-a22b-no-thinking","provider":"Alibaba (Qwen)","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1402.2,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"qwen3-30b-a3b-base","name":"Qwen3-30B-A3B-Base","provider":"Alibaba (Qwen)","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":61.7,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"qwen3-4b","name":"Qwen3-4B","provider":"Alibaba (Qwen)","openWeights":true,"release":"2025-04-29","aliases":["qwen3-4b_none","qwen3-4b"],"page":null,"best":{"gpqa-diamond":{"score":43.56,"unit":"%","sourceType":"independent","date":"2026-08-28","source":"https://epoch.ai/benchmarks"}}},{"id":"qwen3-coder-30b-a3b-instruct","name":"Qwen3-Coder-30B-A3B-Instruct","provider":"Alibaba (Qwen)","openWeights":null,"release":null,"aliases":["EntroPO + R2E + Qwen3-Coder-30B-A3B-Instruct"],"page":null,"best":{"swe-bench-verified":{"score":60.4,"unit":"%","sourceType":"official","date":"2025-09-01","source":"https://www.swebench.com/#verified"}}},{"id":"qwen3-max-preview","name":"qwen3-max-preview","provider":"Alibaba (Qwen)","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1434.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"qwen3-max-thinking-preview","name":"Qwen3-Max-Thinking-Preview","provider":"Alibaba (Qwen)","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"tau2-bench":{"score":75.4,"unit":"%","sourceType":"vendor","date":"2025-10-30","source":"https://qwenlm.github.io/"}}},{"id":"qwen3-next-80b-a3b-instruct","name":"qwen3-next-80b-a3b-instruct","provider":"Alibaba (Qwen)","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1398.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"qwen3-next-80b-a3b","name":"qwen3-next-80b-a3b-thinking","provider":"Alibaba (Qwen)","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1369.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"qwen3-5-0-8b","name":"Qwen3.5-0.8B","provider":"Alibaba (Qwen)","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":29.7,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"qwen3-5-2b","name":"Qwen3.5-2B","provider":"Alibaba (Qwen)","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":55.3,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"qwen3-5-max-preview","name":"qwen3.5-max-preview","provider":"Alibaba (Qwen)","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1464.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"qwen3-7-max-preview","name":"qwen3.7-max-preview","provider":"Alibaba (Qwen)","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1474.9,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"qwen3-8-flash-next","name":"qwen3.8-flash-next","provider":"Alibaba (Qwen)","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-webdev":{"score":1632.6,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"}}},{"id":"qwq-plus","name":"QWQ-Plus","provider":"Alibaba (Qwen)","openWeights":false,"release":"2025-04-08","aliases":["qwq-plus"],"page":null,"best":{"gpqa-diamond":{"score":65.4,"unit":"%","sourceType":"independent","date":"2025-04-11","source":"https://epoch.ai/benchmarks"}}},{"id":"raft-30b-a3b","name":"RAFT-30B-A3B","provider":"Northeastern University HAI Lab","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"tau2-bench":{"score":82.5,"unit":"%","sourceType":"vendor","date":"2026-04-30","source":"https://raft.hailab.io/"}}},{"id":"recurrentgemma-2b","name":"recurrentgemma-2b","provider":"Google","openWeights":true,"release":null,"aliases":["google/recurrentgemma-2b"],"page":null,"best":{"open-llm-leaderboard":{"score":7.02,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"recurrentgemma-2b-it","name":"recurrentgemma-2b-it","provider":"Google","openWeights":true,"release":null,"aliases":["google/recurrentgemma-2b-it"],"page":null,"best":{"open-llm-leaderboard":{"score":8,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"recurrentgemma-9b","name":"recurrentgemma-9b","provider":"Google","openWeights":true,"release":null,"aliases":["google/recurrentgemma-9b"],"page":null,"best":{"open-llm-leaderboard":{"score":13.71,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"recurrentgemma-9b-it","name":"recurrentgemma-9b-it","provider":"Google","openWeights":true,"release":null,"aliases":["google/recurrentgemma-9b-it"],"page":null,"best":{"open-llm-leaderboard":{"score":19.22,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"redpajama-incite-7b-base","name":"RedPajama-INCITE-7B-Base","provider":null,"openWeights":null,"release":"2023-05-04","aliases":["Redpajama-7B"],"page":null,"best":{"mmlu":{"score":26.3,"unit":"%","sourceType":"paper","date":"2023-05-04","source":"http://arxiv.org/abs/2309.03450"}}},{"id":"reflection-llama-3-1-70b","name":"Reflection-Llama-3.1-70B","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":60.35,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"reka-3","name":"Reka 3","provider":"Reka","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":65,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"reka-core","name":"reka-core","provider":"Reka","openWeights":false,"release":null,"aliases":["reka-core-20240904"],"page":null,"best":{"lmarena-text":{"score":1288,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"reka-flash","name":"reka-flash","provider":"Reka","openWeights":false,"release":null,"aliases":["reka-flash-20240904"],"page":null,"best":{"lmarena-text":{"score":1272.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"reka-flash-21b","name":"reka-flash-21b","provider":"Reka","openWeights":false,"release":null,"aliases":["reka-flash-21b-20240226"],"page":null,"best":{"lmarena-text":{"score":1226.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"reka-flash-21b-20240226-online","name":"reka-flash-21b-online","provider":"Reka","openWeights":false,"release":null,"aliases":["reka-flash-21b-20240226-online"],"page":null,"best":{"lmarena-text":{"score":1233.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"ring-flash-2-0","name":"ring-flash-2.0","provider":"ant-group","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1322.8,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"rrd2-5-9b","name":"RRD2.5-9B","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":61.84,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"rwkv-4-raven-14b","name":"RWKV-4-Raven-14B","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1042.3,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"rzn-t","name":"RZN-T","provider":"Phronetic AI","openWeights":true,"release":null,"aliases":["RZN-T (Prompt)"],"page":null,"best":{"bfcl":{"score":22.25,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"santacoder-1-1b","name":"SantaCoder-1.1B","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":14,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"seed-2-1-pro-preview","name":"seed-2.1-pro-preview","provider":"ByteDance","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-webdev":{"score":1519.1,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/webdev"}}},{"id":"seed-thinking-v1-5","name":"Seed-Thinking-v1.5","provider":"ByteDance","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":87,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"seed1-6-ada","name":"Seed1.6-Ada-Thinking","provider":"ByteDance","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":86.4,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"seed1-6-base","name":"Seed1.6-Base","provider":"ByteDance","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":86.6,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"seed1-6","name":"Seed1.6-Thinking","provider":"ByteDance","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":86.6,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"seed2-0-lite","name":"Seed2.0-Lite","provider":"ByteDance","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":87.7,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"seed2-0-mini","name":"Seed2.0-Mini","provider":"ByteDance","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":83.6,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"seed2-0-pro","name":"Seed2.0-Pro","provider":"ByteDance","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":87,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"skythought-t1","name":"SkyThought-T1","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":69.2,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"smollm-1-7b-instruct","name":"SmolLM-1.7B-Instruct","provider":"Hugging Face","openWeights":true,"release":null,"aliases":["HuggingFaceTB/SmolLM-1.7B-Instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":5.49,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"smollm-135m-instruct","name":"SmolLM-135M-Instruct","provider":"Hugging Face","openWeights":true,"release":null,"aliases":["HuggingFaceTB/SmolLM-135M-Instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":3.65,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"smollm-360m-instruct","name":"SmolLM-360M-Instruct","provider":"Hugging Face","openWeights":true,"release":null,"aliases":["HuggingFaceTB/SmolLM-360M-Instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":5.01,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"smollm2-135m-instruct","name":"SmolLM2-135M-Instruct","provider":"Hugging Face","openWeights":true,"release":null,"aliases":["HuggingFaceTB/SmolLM2-135M-Instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":6.47,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"smollm2-360m-instruct","name":"SmolLM2-360M-Instruct","provider":"Hugging Face","openWeights":true,"release":null,"aliases":["HuggingFaceTB/SmolLM2-360M-Instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":8.14,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"snowflake-arctic-instruct","name":"snowflake-arctic-instruct","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1180,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"solar-pro","name":"Solar Pro","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu":{"score":77.6,"unit":"%","sourceType":"official","date":"","source":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"}}},{"id":"solar-10-7b-v1-0","name":"SOLAR-10.7B-v1.0","provider":"upstage","openWeights":true,"release":null,"aliases":["upstage/SOLAR-10.7B-v1.0"],"page":null,"best":{"open-llm-leaderboard":{"score":16.85,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"solar-pro-preview-instruct","name":"solar-pro-preview-instruct","provider":"upstage","openWeights":true,"release":null,"aliases":["upstage/solar-pro-preview-instruct"],"page":null,"best":{"open-llm-leaderboard":{"score":39.94,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"spark-4-0","name":"Spark 4.0-2024-10-14","provider":"iFlytek","openWeights":null,"release":null,"aliases":[],"page":null,"best":{"cmmlu":{"score":90.07,"unit":"%","sourceType":"official","date":"2024-12-06","source":"https://github.com/haonan-li/CMMLU#排行榜"}}},{"id":"speechless-code-mistral-7b-v1-0","name":"speechless-code-mistral-7B-v1.0","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":41.5,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"speechless-codellama-34b-v2-0","name":"speechless-codellama-34B-v2.0","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":72,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"speechless-coder-ds-6-7b","name":"speechless-coder-ds-6.7B","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":65.9,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"speechless-coding-7b-16k-tora","name":"speechless-coding-7B-16k-tora","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":50.6,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"speechless-starcoder2-15b","name":"speechless-starcoder2-15b","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":62.8,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"speechless-starcoder2-7b","name":"speechless-starcoder2-7b","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":51.8,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"stable-code-3b","name":"stable-code-3B","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":25.6,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"stablelm-2-1-6b","name":"stablelm-2-1_6b","provider":"stabilityai","openWeights":true,"release":null,"aliases":["stabilityai/stablelm-2-1_6b"],"page":null,"best":{"open-llm-leaderboard":{"score":5.32,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"stablelm-2-1-6b-chat","name":"stablelm-2-1_6b-chat","provider":"stabilityai","openWeights":true,"release":null,"aliases":["stabilityai/stablelm-2-1_6b-chat"],"page":null,"best":{"open-llm-leaderboard":{"score":8.87,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"stablelm-2-12b","name":"stablelm-2-12b","provider":"stabilityai","openWeights":true,"release":null,"aliases":["stabilityai/stablelm-2-12b"],"page":null,"best":{"open-llm-leaderboard":{"score":14,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"stablelm-2-12b-chat","name":"stablelm-2-12b-chat","provider":"stabilityai","openWeights":true,"release":null,"aliases":["stabilityai/stablelm-2-12b-chat"],"page":null,"best":{"open-llm-leaderboard":{"score":16.78,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"stablelm-2-zephyr-1-6b","name":"stablelm-2-zephyr-1_6b","provider":"stabilityai","openWeights":true,"release":null,"aliases":["stabilityai/stablelm-2-zephyr-1_6b"],"page":null,"best":{"open-llm-leaderboard":{"score":9.46,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"stablelm-3b-4e1t","name":"stablelm-3b-4e1t","provider":"stabilityai","openWeights":true,"release":null,"aliases":["stabilityai/stablelm-3b-4e1t"],"page":null,"best":{"open-llm-leaderboard":{"score":7.33,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"stablelm-7b","name":"StableLM-7B","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":2.4,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"stablelm-tuned-alpha-7b","name":"stablelm-tuned-alpha-7b","provider":null,"openWeights":true,"release":"2023-04-19","aliases":[],"page":null,"best":{"lmarena-text":{"score":953.2,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"stablelm-zephyr-3b","name":"stablelm-zephyr-3b","provider":"stabilityai","openWeights":true,"release":null,"aliases":["stabilityai/stablelm-zephyr-3b"],"page":null,"best":{"open-llm-leaderboard":{"score":12.37,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"starchat2-15b-v0-1","name":"starchat2-15b-v0.1","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":71.3,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"starcoder-15b","name":"StarCoder-15B","provider":"BigCode","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":29.3,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"starcoder2-15b-instruct-v0-1","name":"starcoder2-15b-instruct-v0.1","provider":"BigCode","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":60.4,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"starcoderbase-1b","name":"StarCoderBase-1B","provider":"BigCode","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":12.2,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"starcoderbase-3b","name":"StarCoderBase-3B","provider":"BigCode","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":15.9,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"starcoderbase-7b","name":"StarCoderBase-7B","provider":"BigCode","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":21.3,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"staring-7b","name":"Staring-7B","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu-pro":{"score":37.9,"unit":"%","sourceType":"official","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"starling-lm-7b-alpha","name":"starling-lm-7b-alpha","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1167.4,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"starling-lm-7b-beta","name":"starling-lm-7b-beta","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1171,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"step-3-5-flash","name":"Step 3.5 Flash","provider":"StepFun","openWeights":true,"release":"2026-02-02","aliases":["step-3.5-flash"],"page":null,"best":{"lmarena-text":{"score":1393.2,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"step-1o-vision-32k-highres","name":"step-1o-vision-32k-highres","provider":"StepFun","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-vision":{"score":1124.2,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"step-1v","name":"step-1v-32k","provider":"StepFun","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-vision":{"score":1064.1,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"step-2-16k-exp-202412","name":"step-2-16k-exp-202412","provider":"StepFun","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1333.6,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"stripedhyena-nous-7b","name":"stripedhyena-nous-7b","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1121.6,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"swe-llama","name":"SWE-Llama","provider":"Meta","openWeights":null,"release":null,"aliases":["SWE-Llama 7B","RAG + SWE-Llama 7B"],"page":null,"best":{"swe-bench-verified":{"score":1.4,"unit":"%","sourceType":"official","date":"2023-10-10","source":"https://www.swebench.com/#verified"}}},{"id":"switch-base-8","name":"switch-base-8","provider":"Google","openWeights":true,"release":null,"aliases":["google/switch-base-8"],"page":null,"best":{"open-llm-leaderboard":{"score":3.3,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"seed-oss-36b-base-w-syn","name":"syn.)","provider":"ByteDance","openWeights":null,"release":null,"aliases":["Seed-OSS-36B-Base(w/ syn.)"],"page":null,"best":{"mmlu-pro":{"score":65.1,"unit":"%","sourceType":"vendor","date":"2026-03-11","source":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}}},{"id":"telechat2-35b","name":"Telechat2-35B","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"cmmlu":{"score":90.16,"unit":"%","sourceType":"official","date":"2024-12-06","source":"https://github.com/haonan-li/CMMLU#排行榜"}}},{"id":"toolace-2-8b","name":"ToolACE-2-8B","provider":"Huawei Noah & USTC","openWeights":true,"release":null,"aliases":["ToolACE-2-8B (FC)"],"page":null,"best":{"bfcl":{"score":42.44,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"trinity-large-preview","name":"trinity-large-preview","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1378.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"tulu-2-dpo-70b","name":"tulu-2-dpo-70b","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1177.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"umt5-base","name":"umt5-base","provider":"Google","openWeights":true,"release":null,"aliases":["google/umt5-base"],"page":null,"best":{"open-llm-leaderboard":{"score":3.52,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"vicuna-33b","name":"vicuna-33b","provider":"LMSYS","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1172.9,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"wavecoder-ultra-6-7b","name":"WaveCoder-Ultra-6.7B","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":69.5,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"whiterabbitneo-33b-v1","name":"WhiteRabbitNeo-33B-v1","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":65.9,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"wizardcoder-15b-v1-0","name":"WizardCoder-15B-V1.0","provider":"WizardLM","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":50.6,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"wizardcoder-33b-v1-1","name":"WizardCoder-33B-V1.1","provider":"WizardLM","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":73.2,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"wizardcoder-python-34b-v1-0","name":"WizardCoder-Python-34B-V1.0","provider":"WizardLM","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":64.6,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"wizardcoder-python-7b-v1-0","name":"WizardCoder-Python-7B-V1.0","provider":"WizardLM","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":45.1,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"wizardlm-13b","name":"wizardlm-13b","provider":"Microsoft","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1149.5,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"wizardlm-70b","name":"wizardlm-70b","provider":"Microsoft","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1184.7,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"xbai-o4","name":"XBai-o4-medium","provider":null,"openWeights":null,"release":null,"aliases":["XBai o4-medium"],"page":null,"best":{"livecodebench":{"score":60.4,"unit":"%","sourceType":"official","date":"2025-04-07","source":"https://livecodebench.github.io/leaderboard.html"}}},{"id":"xdan-l1-chat-rl-v1-7b","name":"xDAN-L1-Chat-RL-v1-7B","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":32.9,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"xgen-7b","name":"XGen-7B","provider":"Salesforce","openWeights":true,"release":"2023-06-27","aliases":["xgen-7b-8k-base"],"page":null,"best":{"mmlu":{"score":36.3,"unit":"%","sourceType":"paper","date":"2023-06-27","source":"http://arxiv.org/abs/2309.03450"}}},{"id":"xlam-2-1b-fc-r","name":"xLAM-2-1b-fc-r","provider":"Salesforce","openWeights":true,"release":null,"aliases":["xLAM-2-1b-fc-r (FC)"],"page":null,"best":{"bfcl":{"score":30.44,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"xlam-2-32b-fc-r","name":"xLAM-2-32b-fc-r","provider":"Salesforce","openWeights":true,"release":null,"aliases":["xLAM-2-32b-fc-r (FC)"],"page":null,"best":{"bfcl":{"score":54.66,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"xlam-2-3b-fc-r","name":"xLAM-2-3b-fc-r","provider":"Salesforce","openWeights":true,"release":null,"aliases":["xLAM-2-3b-fc-r (FC)"],"page":null,"best":{"bfcl":{"score":41.22,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"xlam-2-70b-fc-r","name":"xLAM-2-70b-fc-r","provider":"Salesforce","openWeights":true,"release":null,"aliases":["xLAM-2-70b-fc-r (FC)"],"page":null,"best":{"bfcl":{"score":53.07,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"xlam-2-8b-fc-r","name":"xLAM-2-8b-fc-r","provider":"Salesforce","openWeights":true,"release":null,"aliases":["xLAM-2-8b-fc-r (FC)"],"page":null,"best":{"bfcl":{"score":46.68,"unit":"%","sourceType":"official","date":"2026-10-17","source":"https://gorilla.cs.berkeley.edu/leaderboard.html"}}},{"id":"xverse-13b","name":"XVERSE-13B","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"mmlu":{"score":55.21,"unit":"%","sourceType":"paper","date":"","source":"http://arxiv.org/abs/2309.10305"}}},{"id":"xwincoder-34b","name":"XwinCoder-34B","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":69.5,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"yarn-llama-2-13b","name":"Yarn-Llama-2-13b-128k","provider":"NousResearch","openWeights":true,"release":null,"aliases":["NousResearch/Yarn-Llama-2-13b-128k"],"page":null,"best":{"open-llm-leaderboard":{"score":8.49,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"yarn-llama-2-7b","name":"Yarn-Llama-2-7b-64k","provider":"NousResearch","openWeights":true,"release":null,"aliases":["NousResearch/Yarn-Llama-2-7b-64k","NousResearch/Yarn-Llama-2-7b-128k"],"page":null,"best":{"open-llm-leaderboard":{"score":7.22,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"yarn-mistral-7b","name":"Yarn-Mistral-7b-64k","provider":"NousResearch","openWeights":true,"release":null,"aliases":["NousResearch/Yarn-Mistral-7b-64k","NousResearch/Yarn-Mistral-7b-128k"],"page":null,"best":{"open-llm-leaderboard":{"score":13.54,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"yarn-solar-10b","name":"Yarn-Solar-10b-32k","provider":"NousResearch","openWeights":true,"release":null,"aliases":["NousResearch/Yarn-Solar-10b-32k","NousResearch/Yarn-Solar-10b-64k"],"page":null,"best":{"open-llm-leaderboard":{"score":15.72,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"yi-1-5-6b","name":"Yi-1.5-6B","provider":"01.AI","openWeights":true,"release":null,"aliases":["01-ai/Yi-1.5-6B"],"page":null,"best":{"open-llm-leaderboard":{"score":16.75,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"yi-1-5-9b","name":"Yi-1.5-9B","provider":"01.AI","openWeights":true,"release":null,"aliases":["01-ai/Yi-1.5-9B","01-ai/Yi-1.5-9B-32K"],"page":null,"best":{"open-llm-leaderboard":{"score":22.15,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"yi-coder-9b-chat","name":"Yi-Coder-9B-Chat","provider":"01.AI","openWeights":true,"release":null,"aliases":["01-ai/Yi-Coder-9B-Chat"],"page":null,"best":{"open-llm-leaderboard":{"score":16.99,"unit":"%","sourceType":"official","date":"2025-03-13","source":"https://huggingface.co/datasets/open-llm-leaderboard/contents"}}},{"id":"yi-vision","name":"yi-vision","provider":"01.AI","openWeights":false,"release":null,"aliases":[],"page":null,"best":{"lmarena-vision":{"score":1002.4,"unit":"Elo","sourceType":"official","date":"2026-10-02","source":"https://lmarena.ai/leaderboard/vision"}}},{"id":"youyuanjian","name":"Youyuanjian","provider":null,"openWeights":null,"release":null,"aliases":[],"page":null,"best":{"cmmlu":{"score":83.72,"unit":"%","sourceType":"official","date":"2024-12-06","source":"https://github.com/haonan-li/CMMLU#排行榜"}}},{"id":"zephyr-7b","name":"Zephyr β-7B","provider":"Hugging Face","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":23.2,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}},{"id":"zephyr-7b-alpha","name":"zephyr-7b-alpha","provider":"Hugging Face","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1126.9,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"zephyr-orpo-141b-a35b-v0-1","name":"zephyr-orpo-141b-A35b-v0.1","provider":"Hugging Face","openWeights":true,"release":null,"aliases":[],"page":null,"best":{"lmarena-text":{"score":1213,"unit":"Elo","sourceType":"official","date":"2026-10-08","source":"https://lmarena.ai/leaderboard/text"}}},{"id":"zyte-1b","name":"zyte-1B","provider":null,"openWeights":true,"release":null,"aliases":[],"page":null,"best":{"humaneval":{"score":1.8,"unit":"%","sourceType":"official","date":"2024-12-26","source":"https://evalplus.github.io/leaderboard.html"}}}]}