{"source":"AIMap","schema":"benchmark/v1","updated":"2026-10-22","benchmark":{"id":"humaneval","name":"HumanEval / HumanEval+","category":"coding","unit":"%","higherIsBetter":true,"status":"saturated","sources":["evalplus"],"primaryVariant":"humaneval-plus","url":"https://evalplus.github.io/leaderboard.html","year":2021,"desc":{"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）。"},"limits":{"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。"},"contamination":"high","contaminationNote":{"en":"Problems and solutions are all over GitHub.","zh-hans":"题目和答案在 GitHub 上随处可见。"},"stats":{"results":244,"models":122,"latest":"2024-12-26","bySourceType":{"official":244}}},"sources":[{"id":"evalplus","name":"EvalPlus leaderboard","license":"Apache-2.0 (site repo)","policy":"open","attribution":"EvalPlus team, evalplus.github.io","site":"https://evalplus.github.io/leaderboard.html"}],"results":[{"model":"o1-preview-sept-2024","modelName":"O1 Preview (Sept 2024)","provider":"OpenAI","rawName":"O1 Preview (Sept 2024)","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":96.3,"unit":"%","rank":1,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"o1-mini-sept-2024","modelName":"O1 Mini (Sept 2024)","provider":"OpenAI","rawName":"O1 Mini (Sept 2024)","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":96.3,"unit":"%","rank":1,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"gpt-4o-aug-2024","modelName":"GPT-4o (Aug 2024)","provider":"OpenAI","rawName":"GPT 4o (Aug 2024)","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":92.7,"unit":"%","rank":3,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"qwen2-5-coder-32b-instruct","modelName":"Qwen2.5-Coder-32B-Instruct","provider":"Alibaba (Qwen)","rawName":"Qwen2.5-Coder-32B-Instruct","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":92.1,"unit":"%","rank":4,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"deepseek-v3-nov-2024","modelName":"DeepSeek-V3 (Nov 2024)","provider":"DeepSeek","rawName":"DeepSeek-V3 (Nov 2024)","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":91.5,"unit":"%","rank":5,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"deepseek-v2-5-nov-2024","modelName":"DeepSeek-V2.5 (Nov 2024)","provider":"DeepSeek","rawName":"DeepSeek-V2.5 (Nov 2024)","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":90.2,"unit":"%","rank":6,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"gpt-4-turbo-april-2024","modelName":"GPT-4-Turbo (April 2024)","provider":"OpenAI","rawName":"GPT-4-Turbo (April 2024)","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":90.2,"unit":"%","rank":6,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"gemini-1-5-pro-sept-2024","modelName":"Gemini 1.5 Pro (Sept 2024)","provider":"Google","rawName":"Gemini 1.5 Pro 002","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":89,"unit":"%","rank":8,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"grok-beta","modelName":"Grok Beta","provider":"xAI","rawName":"Grok Beta","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":88.4,"unit":"%","rank":9,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"gpt-4o-mini-july-2024","modelName":"GPT 4o Mini (July 2024)","provider":"OpenAI","rawName":"GPT 4o Mini (July 2024)","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":88.4,"unit":"%","rank":9,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"gpt-4-may-2023","modelName":"GPT-4 (May 2023)","provider":"OpenAI","rawName":"GPT-4 (May 2023)","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":88.4,"unit":"%","rank":9,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"claude-sonnet-3-5-june-2024","modelName":"Claude Sonnet 3.5 (June 2024)","provider":"Anthropic","rawName":"Claude Sonnet 3.5 (June 2024)","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":87.2,"unit":"%","rank":12,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"deepseek-coder-v2-236b","modelName":"DeepSeek-Coder-V2 236B","provider":"DeepSeek","rawName":"DeepSeek-Coder-V2-Instruct","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":85.4,"unit":"%","rank":13,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"gpt-4-turbo-nov-2023","modelName":"GPT-4 Turbo (Nov 2023)","provider":"OpenAI","rawName":"GPT-4-Turbo (Nov 2023)","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":85.4,"unit":"%","rank":13,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"codeqwen1-5-7b-chat","modelName":"CodeQwen1.5-7B-Chat","provider":"Alibaba (Qwen)","rawName":"CodeQwen1.5-7B-Chat","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":83.5,"unit":"%","rank":15,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"claude-3-opus-mar-2024","modelName":"claude-3-opus (Mar 2024)","provider":"Anthropic","rawName":"claude-3-opus (Mar 2024)","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":82.9,"unit":"%","rank":16,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"gemini-1-5-flash-sep-2024","modelName":"Gemini 1.5 Flash (Sep 2024)","provider":"Google","rawName":"Gemini 1.5 Flash 002","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":82.3,"unit":"%","rank":17,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"opencoder-8b-instruct","modelName":"OpenCoder-8B-Instruct","provider":null,"rawName":"OpenCoder-8B-Instruct","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":81.7,"unit":"%","rank":18,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"codestral-22b-v0-1","modelName":"Codestral-22B-v0.1","provider":"Mistral AI","rawName":"Codestral-22B-v0.1","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":79.9,"unit":"%","rank":19,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"wizardcoder-33b-v1-1","modelName":"WizardCoder-33B-V1.1","provider":"WizardLM","rawName":"WizardCoder-33B-V1.1","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":79.9,"unit":"%","rank":19,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"opencodeinterpreter-ds-33b","modelName":"OpenCodeInterpreter-DS-33B","provider":null,"rawName":"OpenCodeInterpreter-DS-33B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":79.3,"unit":"%","rank":21,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"llama3-70b-instruct","modelName":"Llama3-70B-instruct","provider":"Meta","rawName":"Llama3-70B-instruct","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":77.4,"unit":"%","rank":22,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"opencodeinterpreter-ds-6-7b","modelName":"OpenCodeInterpreter-DS-6.7B","provider":null,"rawName":"OpenCodeInterpreter-DS-6.7B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":77.4,"unit":"%","rank":22,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"speechless-codellama-34b-v2-0","modelName":"speechless-codellama-34B-v2.0","provider":null,"rawName":"speechless-codellama-34B-v2.0","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":77.4,"unit":"%","rank":22,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"gpt-3-5-turbo-nov-2023","modelName":"GPT-3.5 Turbo (Nov 2023)","provider":"OpenAI","rawName":"GPT-3.5-Turbo (Nov 2023)","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":76.8,"unit":"%","rank":25,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"magicoder-s-ds-6-7b","modelName":"Magicoder-S-DS-6.7B","provider":null,"rawName":"Magicoder-S-DS-6.7B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":76.8,"unit":"%","rank":25,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"claude-3-haiku-mar-2024","modelName":"claude-3-haiku (Mar 2024)","provider":"Anthropic","rawName":"claude-3-haiku (Mar 2024)","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":76.8,"unit":"%","rank":25,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"mixtral-8x22b","modelName":"Mixtral 8x22B","provider":"Mistral AI","rawName":"Mixtral-8x22B-Instruct-v0.1","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":76.2,"unit":"%","rank":28,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"artigenz-coder-ds-6-7b","modelName":"Artigenz-Coder-DS-6.7B","provider":null,"rawName":"Artigenz-Coder-DS-6.7B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":75.6,"unit":"%","rank":29,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"deepseek-coder-7b-instruct-v1-5","modelName":"DeepSeek-Coder-7B-instruct-v1.5","provider":"DeepSeek","rawName":"DeepSeek-Coder-7B-instruct-v1.5","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":75.6,"unit":"%","rank":29,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"xwincoder-34b","modelName":"XwinCoder-34B","provider":null,"rawName":"XwinCoder-34B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":75.6,"unit":"%","rank":29,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"wavecoder-ultra-6-7b","modelName":"WaveCoder-Ultra-6.7B","provider":null,"rawName":"WaveCoder-Ultra-6.7B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":75,"unit":"%","rank":32,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"dbrx","modelName":"DBRX","provider":"Databricks","rawName":"databricks/dbrx-instruct","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":75,"unit":"%","rank":32,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"code-millenials-34b","modelName":"code-millenials-34B","provider":null,"rawName":"code-millenials-34B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":74.4,"unit":"%","rank":34,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"starchat2-15b-v0-1","modelName":"starchat2-15b-v0.1","provider":null,"rawName":"starchat2-15b-v0.1","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":73.8,"unit":"%","rank":35,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"gpt-3-5-may-2023","modelName":"GPT-3.5 (May 2023)","provider":"OpenAI","rawName":"GPT-3.5 (May 2023)","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":73.2,"unit":"%","rank":36,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"wizardcoder-python-34b-v1-0","modelName":"WizardCoder-Python-34B-V1.0","provider":"WizardLM","rawName":"WizardCoder-Python-34B-V1.0","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":73.2,"unit":"%","rank":36,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"openchat-3-5-7b-0106","modelName":"OpenChat-3.5-7B-0106","provider":null,"rawName":"OpenChat-3.5-7B-0106","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":72.6,"unit":"%","rank":38,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"codellama-70b-instruct","modelName":"codellama-70b-instruct","provider":"Meta","rawName":"CodeLlama-70B-Instruct","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":72,"unit":"%","rank":39,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"whiterabbitneo-33b-v1","modelName":"WhiteRabbitNeo-33B-v1","provider":null,"rawName":"WhiteRabbitNeo-33B-v1","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":72,"unit":"%","rank":39,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"phind-codellama-34b-v2","modelName":"Phind-CodeLlama-34B-v2","provider":null,"rawName":"Phind-CodeLlama-34B-v2","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":71.3,"unit":"%","rank":41,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"speechless-coder-ds-6-7b","modelName":"speechless-coder-ds-6.7B","provider":null,"rawName":"speechless-coder-ds-6.7B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":71.3,"unit":"%","rank":41,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"magicoder-s-cl-7b","modelName":"Magicoder-S-CL-7B","provider":null,"rawName":"Magicoder-S-CL-7B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":70.7,"unit":"%","rank":43,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"claude-3-sonnet-mar-2024","modelName":"claude-3-sonnet (Mar 2024)","provider":"Anthropic","rawName":"claude-3-sonnet (Mar 2024)","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":70.7,"unit":"%","rank":43,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"llama3-1-8b-instruct","modelName":"Llama3.1-8B-instruct","provider":"Meta","rawName":"Llama3.1-8B-instruct","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":69.5,"unit":"%","rank":45,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"mistral-large-mar-2024","modelName":"Mistral Large (Mar 2024)","provider":"Mistral AI","rawName":"Mistral Large (Mar 2024)","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":69.5,"unit":"%","rank":45,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"claude-2-mar-2024","modelName":"claude-2 (Mar 2024)","provider":"Anthropic","rawName":"claude-2 (Mar 2024)","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":69.5,"unit":"%","rank":45,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"qwen1-5-72b","modelName":"Qwen1.5-72B","provider":"Alibaba (Qwen)","rawName":"Qwen1.5-72B-Chat","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":68.3,"unit":"%","rank":48,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"gemini-pro-1-5","modelName":"Gemini Pro 1.5","provider":"Google","rawName":"Gemini Pro 1.5","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":68.3,"unit":"%","rank":48,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"starcoder2-15b-instruct-v0-1","modelName":"starcoder2-15b-instruct-v0.1","provider":"BigCode","rawName":"starcoder2-15b-instruct-v0.1","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":67.7,"unit":"%","rank":50,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"speechless-starcoder2-15b","modelName":"speechless-starcoder2-15b","provider":null,"rawName":"speechless-starcoder2-15b","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":67.1,"unit":"%","rank":51,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"code-290k-6-7b-instruct","modelName":"Code-290k-6.7B-Instruct","provider":null,"rawName":"Code-290k-6.7B-Instruct","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":64.6,"unit":"%","rank":52,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"phi-3-mini-3-8b","modelName":"phi-3-mini 3.8B","provider":"Microsoft","rawName":"Phi-3-mini-4k-instruct","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":64.6,"unit":"%","rank":52,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"command-r","modelName":"Command R+","provider":"Cohere","rawName":"Command-R+","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":64,"unit":"%","rank":54,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"dolphin-2-6-mixtral-8x7b","modelName":"dolphin-2.6-mixtral-8x7b","provider":null,"rawName":"dolphin-2.6-mixtral-8x7b","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":64,"unit":"%","rank":54,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"gemini-pro-1-0","modelName":"Gemini Pro 1.0","provider":"Google","rawName":"Gemini Pro 1.0","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":63.4,"unit":"%","rank":56,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"llama3-8b-instruct","modelName":"Llama3-8B-instruct","provider":"Meta","rawName":"Llama3-8B-instruct","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":61.6,"unit":"%","rank":57,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"codegemma-7b-it","modelName":"codegemma-7b-it","provider":"Google","rawName":"codegemma-7b-it","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":60.4,"unit":"%","rank":58,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"claude-instant-1-mar-2024","modelName":"claude-instant-1 (Mar 2024)","provider":"Anthropic","rawName":"claude-instant-1 (Mar 2024)","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":57.3,"unit":"%","rank":59,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"wizardcoder-15b-v1-0","modelName":"WizardCoder-15B-V1.0","provider":"WizardLM","rawName":"WizardCoder-15B-V1.0","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":56.7,"unit":"%","rank":60,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"code-13b","modelName":"Code-13B","provider":null,"rawName":"Code-13B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":56.1,"unit":"%","rank":61,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"speechless-starcoder2-7b","modelName":"speechless-starcoder2-7b","provider":null,"rawName":"speechless-starcoder2-7b","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":56.1,"unit":"%","rank":61,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"codellama-70b","modelName":"CodeLlama-70B","provider":"Meta","rawName":"CodeLlama-70B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":55.5,"unit":"%","rank":63,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"code-33b","modelName":"Code-33B","provider":null,"rawName":"Code-33B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":54.9,"unit":"%","rank":64,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"speechless-coding-7b-16k-tora","modelName":"speechless-coding-7B-16k-tora","provider":null,"rawName":"speechless-coding-7B-16k-tora","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":54.9,"unit":"%","rank":64,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"openhermes-2-5-code-290k-13b","modelName":"OpenHermes-2.5-Code-290k-13B","provider":null,"rawName":"OpenHermes-2.5-Code-290k-13B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":54.3,"unit":"%","rank":66,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"codellama-34b","modelName":"CodeLlama-34B","provider":"Meta","rawName":"CodeLlama-34B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":51.8,"unit":"%","rank":67,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"codeqwen1-5-7b","modelName":"CodeQwen1.5-7B","provider":"Alibaba (Qwen)","rawName":"CodeQwen1.5-7B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":51.8,"unit":"%","rank":67,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"deepseek-coder-33b","modelName":"DeepSeek Coder 33B","provider":"DeepSeek","rawName":"DeepSeek-Coder-33B-base","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":51.2,"unit":"%","rank":69,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"wizardcoder-python-7b-v1-0","modelName":"WizardCoder-Python-7B-V1.0","provider":"WizardLM","rawName":"WizardCoder-Python-7B-V1.0","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":50.6,"unit":"%","rank":70,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"phi-2-2-7b","modelName":"phi-2-2.7B","provider":"Microsoft","rawName":"phi-2-2.7B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":49.4,"unit":"%","rank":71,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"mistral-codealpaca-7b","modelName":"Mistral-codealpaca-7B","provider":"Mistral AI","rawName":"Mistral-codealpaca-7B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":48.2,"unit":"%","rank":72,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"speechless-code-mistral-7b-v1-0","modelName":"speechless-code-mistral-7B-v1.0","provider":null,"rawName":"speechless-code-mistral-7B-v1.0","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":48.2,"unit":"%","rank":72,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"deepseek-coder-6-7b","modelName":"DeepSeek Coder 6.7B","provider":"DeepSeek","rawName":"DeepSeek-Coder-6.7B-base","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":47.6,"unit":"%","rank":74,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"mistralhermes-codepro-7b-v1","modelName":"MistralHermes-CodePro-7B-v1","provider":"Mistral AI","rawName":"MistralHermes-CodePro-7B-v1","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":47.6,"unit":"%","rank":74,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"starcoder-2-15b","modelName":"StarCoder 2 15B","provider":"Hugging Face","rawName":"StarCoder2-15B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":46.3,"unit":"%","rank":76,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"mixtral-8x7b","modelName":"Mixtral 8x7B","provider":"Mistral AI","rawName":"Mixtral-8x7B-Instruct-v0.1","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":45.1,"unit":"%","rank":77,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"codegemma-7b","modelName":"codegemma-7b","provider":"Google","rawName":"codegemma-7b","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":44.5,"unit":"%","rank":78,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"solar-10-7b-instruct-v1-0","modelName":"solar-10.7b-instruct-v1.0","provider":"upstage","rawName":"SOLAR-10.7B-Instruct-v1.0","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":43.3,"unit":"%","rank":79,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"codellama-13b","modelName":"CodeLlama-13B","provider":"Meta","rawName":"CodeLlama-13B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":42.7,"unit":"%","rank":80,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"gemma-1-1-7b-it","modelName":"gemma-1.1-7b-it","provider":"Google","rawName":"gemma-1.1-7b-it","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":42.7,"unit":"%","rank":80,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"mistral-7b-v0-2","modelName":"Mistral 7B v0.2","provider":"Mistral AI","rawName":"Mistral-7B-Instruct-v0.2","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":42.1,"unit":"%","rank":82,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"xdan-l1-chat-rl-v1-7b","modelName":"xDAN-L1-Chat-RL-v1-7B","provider":null,"rawName":"xDAN-L1-Chat-RL-v1-7B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":40.2,"unit":"%","rank":83,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"codellama-7b","modelName":"CodeLlama-7B","provider":"Meta","rawName":"CodeLlama-7B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":37.8,"unit":"%","rank":84,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"starcoder-2-7b","modelName":"StarCoder 2 7B","provider":"Hugging Face","rawName":"StarCoder2-7B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":35.4,"unit":"%","rank":85,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"gemma-7b","modelName":"Gemma 7B","provider":"Google","rawName":"gemma-7b","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":35.4,"unit":"%","rank":85,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"starcoder-15b","modelName":"StarCoder-15B","provider":"BigCode","rawName":"StarCoder-15B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":34.1,"unit":"%","rank":87,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"llama3-8b-base","modelName":"Llama3-8B-base","provider":"Meta","rawName":"Llama3-8B-base","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":33.5,"unit":"%","rank":88,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"codegen-16b","modelName":"CodeGen-16B","provider":null,"rawName":"CodeGen-16B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":32.9,"unit":"%","rank":89,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"python-code-13b","modelName":"Python-Code-13B","provider":null,"rawName":"Python-Code-13B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":32.9,"unit":"%","rank":89,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"codet5-16b","modelName":"CodeT5+-16B","provider":null,"rawName":"CodeT5+-16B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":31.7,"unit":"%","rank":91,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"starcoder-2-3b","modelName":"StarCoder 2 3B","provider":"Hugging Face","rawName":"StarCoder2-3B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":31.7,"unit":"%","rank":91,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"zephyr-7b","modelName":"Zephyr β-7B","provider":"Hugging Face","rawName":"Zephyr β-7B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":30,"unit":"%","rank":93,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"codegen-6b","modelName":"CodeGen-6B","provider":null,"rawName":"CodeGen-6B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":29.3,"unit":"%","rank":94,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"codet5-6b","modelName":"CodeT5+-6B","provider":null,"rawName":"CodeT5+-6B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":29.3,"unit":"%","rank":94,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"stable-code-3b","modelName":"stable-code-3B","provider":null,"rawName":"stable-code-3B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":29.3,"unit":"%","rank":94,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"deepseek-coder-1-3b","modelName":"DeepSeek Coder 1.3B","provider":"DeepSeek","rawName":"DeepSeek-Coder-1.3B-base","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":28.7,"unit":"%","rank":97,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"mistral-7b","modelName":"Mistral-7B","provider":"Mistral AI","rawName":"Mistral-7B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":28.7,"unit":"%","rank":97,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"gemma-7b-it","modelName":"gemma-7b-it","provider":"Google","rawName":"gemma-7b-it","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":28.7,"unit":"%","rank":97,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"codegemma-2b","modelName":"codegemma-2b","provider":"Google","rawName":"codegemma-2b","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":26.8,"unit":"%","rank":100,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"codet5-2b","modelName":"CodeT5+-2B","provider":null,"rawName":"CodeT5+-2B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":25,"unit":"%","rank":101,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"gemma-2b","modelName":"Gemma 2B","provider":"Google","rawName":"gemma-2b","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":25,"unit":"%","rank":101,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"codegen-2b","modelName":"CodeGen-2B","provider":null,"rawName":"CodeGen-2B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":24.4,"unit":"%","rank":103,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"starcoderbase-7b","modelName":"StarCoderBase-7B","provider":"BigCode","rawName":"StarCoderBase-7B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":24.4,"unit":"%","rank":103,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"gemma-1-1-2b-it","modelName":"gemma-1.1-2b-it","provider":"Google","rawName":"gemma-1.1-2b-it","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":22.6,"unit":"%","rank":105,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"codegen2-16b","modelName":"CodeGen2-16B","provider":null,"rawName":"CodeGen2-16B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":19.5,"unit":"%","rank":106,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"codegen2-7b","modelName":"CodeGen2-7B","provider":null,"rawName":"CodeGen2-7B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":18.3,"unit":"%","rank":107,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"starcoderbase-3b","modelName":"StarCoderBase-3B","provider":"BigCode","rawName":"StarCoderBase-3B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":17.7,"unit":"%","rank":108,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"gemma-2b-it","modelName":"gemma-2b-it","provider":"Google","rawName":"gemma-2b-it","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":17.7,"unit":"%","rank":108,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"vicuna-13b","modelName":"Vicuna-13B","provider":"LMSYS","rawName":"Vicuna-13B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":17.1,"unit":"%","rank":110,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"codegen2-3b","modelName":"CodeGen2-3B","provider":null,"rawName":"CodeGen2-3B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":15.9,"unit":"%","rank":111,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"incoder-6-7b","modelName":"InCoder-6.7B","provider":null,"rawName":"InCoder-6.7B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":15.9,"unit":"%","rank":111,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"santacoder-1-1b","modelName":"SantaCoder-1.1B","provider":null,"rawName":"SantaCoder-1.1B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":14.6,"unit":"%","rank":113,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"starcoderbase-1b","modelName":"StarCoderBase-1B","provider":"BigCode","rawName":"StarCoderBase-1B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":14.6,"unit":"%","rank":113,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"gpt-j-6b","modelName":"GPT-J-6B","provider":"EleutherAI","rawName":"GPT-J-6B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":12.2,"unit":"%","rank":115,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"incoder-1-3b","modelName":"InCoder-1.3B","provider":null,"rawName":"InCoder-1.3B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":12.2,"unit":"%","rank":115,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"vicuna-7b","modelName":"vicuna-7b","provider":"LMSYS","rawName":"Vicuna-7B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":11.6,"unit":"%","rank":117,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"codegen2-1b","modelName":"CodeGen2-1B","provider":null,"rawName":"CodeGen2-1B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":11,"unit":"%","rank":118,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"gpt-neo-2-7b","modelName":"GPT-Neo-2.7B","provider":"EleutherAI","rawName":"GPT-Neo-2.7B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":7.9,"unit":"%","rank":119,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"polycoder-2-7b","modelName":"PolyCoder-2.7B","provider":null,"rawName":"PolyCoder-2.7B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":6.1,"unit":"%","rank":120,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"stablelm-7b","modelName":"StableLM-7B","provider":null,"rawName":"StableLM-7B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":2.4,"unit":"%","rank":121,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"zyte-1b","modelName":"zyte-1B","provider":null,"rawName":"zyte-1B","variant":"humaneval","setting":"HumanEval (base tests), pass@1 greedy","score":2.4,"unit":"%","rank":121,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"o1-preview-sept-2024","modelName":"O1 Preview (Sept 2024)","provider":"OpenAI","rawName":"O1 Preview (Sept 2024)","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":89,"unit":"%","rank":1,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"o1-mini-sept-2024","modelName":"O1 Mini (Sept 2024)","provider":"OpenAI","rawName":"O1 Mini (Sept 2024)","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":89,"unit":"%","rank":1,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"qwen2-5-coder-32b-instruct","modelName":"Qwen2.5-Coder-32B-Instruct","provider":"Alibaba (Qwen)","rawName":"Qwen2.5-Coder-32B-Instruct","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":87.2,"unit":"%","rank":3,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"gpt-4o-aug-2024","modelName":"GPT-4o (Aug 2024)","provider":"OpenAI","rawName":"GPT 4o (Aug 2024)","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":87.2,"unit":"%","rank":3,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"deepseek-v3-nov-2024","modelName":"DeepSeek-V3 (Nov 2024)","provider":"DeepSeek","rawName":"DeepSeek-V3 (Nov 2024)","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":86.6,"unit":"%","rank":5,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"gpt-4-turbo-april-2024","modelName":"GPT-4-Turbo (April 2024)","provider":"OpenAI","rawName":"GPT-4-Turbo (April 2024)","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":86.6,"unit":"%","rank":5,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"deepseek-v2-5-nov-2024","modelName":"DeepSeek-V2.5 (Nov 2024)","provider":"DeepSeek","rawName":"DeepSeek-V2.5 (Nov 2024)","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":83.5,"unit":"%","rank":7,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"gpt-4o-mini-july-2024","modelName":"GPT 4o Mini (July 2024)","provider":"OpenAI","rawName":"GPT 4o Mini (July 2024)","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":83.5,"unit":"%","rank":7,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"deepseek-coder-v2-236b","modelName":"DeepSeek-Coder-V2 236B","provider":"DeepSeek","rawName":"DeepSeek-Coder-V2-Instruct","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":82.3,"unit":"%","rank":9,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"claude-sonnet-3-5-june-2024","modelName":"Claude Sonnet 3.5 (June 2024)","provider":"Anthropic","rawName":"Claude Sonnet 3.5 (June 2024)","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":81.7,"unit":"%","rank":10,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"gpt-4-turbo-nov-2023","modelName":"GPT-4 Turbo (Nov 2023)","provider":"OpenAI","rawName":"GPT-4-Turbo (Nov 2023)","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":81.7,"unit":"%","rank":10,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"grok-beta","modelName":"Grok Beta","provider":"xAI","rawName":"Grok Beta","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":80.5,"unit":"%","rank":12,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"gemini-1-5-pro-sept-2024","modelName":"Gemini 1.5 Pro (Sept 2024)","provider":"Google","rawName":"Gemini 1.5 Pro 002","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":79.3,"unit":"%","rank":13,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"gpt-4-may-2023","modelName":"GPT-4 (May 2023)","provider":"OpenAI","rawName":"GPT-4 (May 2023)","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":79.3,"unit":"%","rank":13,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"codeqwen1-5-7b-chat","modelName":"CodeQwen1.5-7B-Chat","provider":"Alibaba (Qwen)","rawName":"CodeQwen1.5-7B-Chat","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":78.7,"unit":"%","rank":15,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"opencoder-8b-instruct","modelName":"OpenCoder-8B-Instruct","provider":null,"rawName":"OpenCoder-8B-Instruct","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":77.4,"unit":"%","rank":16,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"claude-3-opus-mar-2024","modelName":"claude-3-opus (Mar 2024)","provider":"Anthropic","rawName":"claude-3-opus (Mar 2024)","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":77.4,"unit":"%","rank":16,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"gemini-1-5-flash-sep-2024","modelName":"Gemini 1.5 Flash (Sep 2024)","provider":"Google","rawName":"Gemini 1.5 Flash 002","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":75.6,"unit":"%","rank":18,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"codestral-22b-v0-1","modelName":"Codestral-22B-v0.1","provider":"Mistral AI","rawName":"Codestral-22B-v0.1","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":73.8,"unit":"%","rank":19,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"opencodeinterpreter-ds-33b","modelName":"OpenCodeInterpreter-DS-33B","provider":null,"rawName":"OpenCodeInterpreter-DS-33B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":73.8,"unit":"%","rank":19,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"wizardcoder-33b-v1-1","modelName":"WizardCoder-33B-V1.1","provider":"WizardLM","rawName":"WizardCoder-33B-V1.1","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":73.2,"unit":"%","rank":21,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"artigenz-coder-ds-6-7b","modelName":"Artigenz-Coder-DS-6.7B","provider":null,"rawName":"Artigenz-Coder-DS-6.7B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":72.6,"unit":"%","rank":22,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"llama3-70b-instruct","modelName":"Llama3-70B-instruct","provider":"Meta","rawName":"Llama3-70B-instruct","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":72,"unit":"%","rank":23,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"mixtral-8x22b","modelName":"Mixtral 8x22B","provider":"Mistral AI","rawName":"Mixtral-8x22B-Instruct-v0.1","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":72,"unit":"%","rank":23,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"opencodeinterpreter-ds-6-7b","modelName":"OpenCodeInterpreter-DS-6.7B","provider":null,"rawName":"OpenCodeInterpreter-DS-6.7B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":72,"unit":"%","rank":23,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"speechless-codellama-34b-v2-0","modelName":"speechless-codellama-34B-v2.0","provider":null,"rawName":"speechless-codellama-34B-v2.0","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":72,"unit":"%","rank":23,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"deepseek-coder-7b-instruct-v1-5","modelName":"DeepSeek-Coder-7B-instruct-v1.5","provider":"DeepSeek","rawName":"DeepSeek-Coder-7B-instruct-v1.5","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":71.3,"unit":"%","rank":27,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"magicoder-s-ds-6-7b","modelName":"Magicoder-S-DS-6.7B","provider":null,"rawName":"Magicoder-S-DS-6.7B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":71.3,"unit":"%","rank":27,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"starchat2-15b-v0-1","modelName":"starchat2-15b-v0.1","provider":null,"rawName":"starchat2-15b-v0.1","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":71.3,"unit":"%","rank":27,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"gpt-3-5-turbo-nov-2023","modelName":"GPT-3.5 Turbo (Nov 2023)","provider":"OpenAI","rawName":"GPT-3.5-Turbo (Nov 2023)","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":70.7,"unit":"%","rank":30,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"code-millenials-34b","modelName":"code-millenials-34B","provider":null,"rawName":"code-millenials-34B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":70.7,"unit":"%","rank":30,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"dbrx","modelName":"DBRX","provider":"Databricks","rawName":"databricks/dbrx-instruct","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":70.1,"unit":"%","rank":32,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"wavecoder-ultra-6-7b","modelName":"WaveCoder-Ultra-6.7B","provider":null,"rawName":"WaveCoder-Ultra-6.7B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":69.5,"unit":"%","rank":33,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"xwincoder-34b","modelName":"XwinCoder-34B","provider":null,"rawName":"XwinCoder-34B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":69.5,"unit":"%","rank":33,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"claude-3-haiku-mar-2024","modelName":"claude-3-haiku (Mar 2024)","provider":"Anthropic","rawName":"claude-3-haiku (Mar 2024)","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":68.9,"unit":"%","rank":35,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"magicoder-s-cl-7b","modelName":"Magicoder-S-CL-7B","provider":null,"rawName":"Magicoder-S-CL-7B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":67.7,"unit":"%","rank":36,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"openchat-3-5-7b-0106","modelName":"OpenChat-3.5-7B-0106","provider":null,"rawName":"OpenChat-3.5-7B-0106","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":67.7,"unit":"%","rank":36,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"phind-codellama-34b-v2","modelName":"Phind-CodeLlama-34B-v2","provider":null,"rawName":"Phind-CodeLlama-34B-v2","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":67.1,"unit":"%","rank":38,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"gpt-3-5-may-2023","modelName":"GPT-3.5 (May 2023)","provider":"OpenAI","rawName":"GPT-3.5 (May 2023)","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":66.5,"unit":"%","rank":39,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"codellama-70b-instruct","modelName":"codellama-70b-instruct","provider":"Meta","rawName":"CodeLlama-70B-Instruct","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":65.9,"unit":"%","rank":40,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"whiterabbitneo-33b-v1","modelName":"WhiteRabbitNeo-33B-v1","provider":null,"rawName":"WhiteRabbitNeo-33B-v1","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":65.9,"unit":"%","rank":40,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"speechless-coder-ds-6-7b","modelName":"speechless-coder-ds-6.7B","provider":null,"rawName":"speechless-coder-ds-6.7B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":65.9,"unit":"%","rank":40,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"wizardcoder-python-34b-v1-0","modelName":"WizardCoder-Python-34B-V1.0","provider":"WizardLM","rawName":"WizardCoder-Python-34B-V1.0","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":64.6,"unit":"%","rank":43,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"claude-3-sonnet-mar-2024","modelName":"claude-3-sonnet (Mar 2024)","provider":"Anthropic","rawName":"claude-3-sonnet (Mar 2024)","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":64,"unit":"%","rank":44,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"llama3-1-8b-instruct","modelName":"Llama3.1-8B-instruct","provider":"Meta","rawName":"Llama3.1-8B-instruct","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":62.8,"unit":"%","rank":45,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"speechless-starcoder2-15b","modelName":"speechless-starcoder2-15b","provider":null,"rawName":"speechless-starcoder2-15b","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":62.8,"unit":"%","rank":45,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"mistral-large-mar-2024","modelName":"Mistral Large (Mar 2024)","provider":"Mistral AI","rawName":"Mistral Large (Mar 2024)","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":62.2,"unit":"%","rank":47,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"claude-2-mar-2024","modelName":"claude-2 (Mar 2024)","provider":"Anthropic","rawName":"claude-2 (Mar 2024)","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":61.6,"unit":"%","rank":48,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"gemini-pro-1-5","modelName":"Gemini Pro 1.5","provider":"Google","rawName":"Gemini Pro 1.5","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":61,"unit":"%","rank":49,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"starcoder2-15b-instruct-v0-1","modelName":"starcoder2-15b-instruct-v0.1","provider":"BigCode","rawName":"starcoder2-15b-instruct-v0.1","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":60.4,"unit":"%","rank":50,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"code-290k-6-7b-instruct","modelName":"Code-290k-6.7B-Instruct","provider":null,"rawName":"Code-290k-6.7B-Instruct","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":59.7,"unit":"%","rank":51,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"qwen1-5-72b","modelName":"Qwen1.5-72B","provider":"Alibaba (Qwen)","rawName":"Qwen1.5-72B-Chat","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":59.1,"unit":"%","rank":52,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"phi-3-mini-3-8b","modelName":"phi-3-mini 3.8B","provider":"Microsoft","rawName":"Phi-3-mini-4k-instruct","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":59.1,"unit":"%","rank":52,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"dolphin-2-6-mixtral-8x7b","modelName":"dolphin-2.6-mixtral-8x7b","provider":null,"rawName":"dolphin-2.6-mixtral-8x7b","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":57.3,"unit":"%","rank":54,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"command-r","modelName":"Command R+","provider":"Cohere","rawName":"Command-R+","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":56.7,"unit":"%","rank":55,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"llama3-8b-instruct","modelName":"Llama3-8B-instruct","provider":"Meta","rawName":"Llama3-8B-instruct","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":56.7,"unit":"%","rank":55,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"gemini-pro-1-0","modelName":"Gemini Pro 1.0","provider":"Google","rawName":"Gemini Pro 1.0","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":55.5,"unit":"%","rank":57,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"code-13b","modelName":"Code-13B","provider":null,"rawName":"Code-13B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":52.4,"unit":"%","rank":58,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"codegemma-7b-it","modelName":"codegemma-7b-it","provider":"Google","rawName":"codegemma-7b-it","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":51.8,"unit":"%","rank":59,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"speechless-starcoder2-7b","modelName":"speechless-starcoder2-7b","provider":null,"rawName":"speechless-starcoder2-7b","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":51.8,"unit":"%","rank":59,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"codellama-70b","modelName":"CodeLlama-70B","provider":"Meta","rawName":"CodeLlama-70B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":50.6,"unit":"%","rank":61,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"wizardcoder-15b-v1-0","modelName":"WizardCoder-15B-V1.0","provider":"WizardLM","rawName":"WizardCoder-15B-V1.0","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":50.6,"unit":"%","rank":61,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"claude-instant-1-mar-2024","modelName":"claude-instant-1 (Mar 2024)","provider":"Anthropic","rawName":"claude-instant-1 (Mar 2024)","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":50.6,"unit":"%","rank":61,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"speechless-coding-7b-16k-tora","modelName":"speechless-coding-7B-16k-tora","provider":null,"rawName":"speechless-coding-7B-16k-tora","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":50.6,"unit":"%","rank":61,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"code-33b","modelName":"Code-33B","provider":null,"rawName":"Code-33B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":49.4,"unit":"%","rank":65,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"openhermes-2-5-code-290k-13b","modelName":"OpenHermes-2.5-Code-290k-13B","provider":null,"rawName":"OpenHermes-2.5-Code-290k-13B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":48.8,"unit":"%","rank":66,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"codeqwen1-5-7b","modelName":"CodeQwen1.5-7B","provider":"Alibaba (Qwen)","rawName":"CodeQwen1.5-7B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":45.7,"unit":"%","rank":67,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"wizardcoder-python-7b-v1-0","modelName":"WizardCoder-Python-7B-V1.0","provider":"WizardLM","rawName":"WizardCoder-Python-7B-V1.0","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":45.1,"unit":"%","rank":68,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"phi-2-2-7b","modelName":"phi-2-2.7B","provider":"Microsoft","rawName":"phi-2-2.7B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":45.1,"unit":"%","rank":68,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"deepseek-coder-33b","modelName":"DeepSeek Coder 33B","provider":"DeepSeek","rawName":"DeepSeek-Coder-33B-base","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":44.5,"unit":"%","rank":70,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"codellama-34b","modelName":"CodeLlama-34B","provider":"Meta","rawName":"CodeLlama-34B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":43.9,"unit":"%","rank":71,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"mistral-codealpaca-7b","modelName":"Mistral-codealpaca-7B","provider":"Mistral AI","rawName":"Mistral-codealpaca-7B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":42.1,"unit":"%","rank":72,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"mistralhermes-codepro-7b-v1","modelName":"MistralHermes-CodePro-7B-v1","provider":"Mistral AI","rawName":"MistralHermes-CodePro-7B-v1","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":42.1,"unit":"%","rank":72,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"codegemma-7b","modelName":"codegemma-7b","provider":"Google","rawName":"codegemma-7b","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":41.5,"unit":"%","rank":74,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"speechless-code-mistral-7b-v1-0","modelName":"speechless-code-mistral-7B-v1.0","provider":null,"rawName":"speechless-code-mistral-7B-v1.0","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":41.5,"unit":"%","rank":74,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"deepseek-coder-6-7b","modelName":"DeepSeek Coder 6.7B","provider":"DeepSeek","rawName":"DeepSeek-Coder-6.7B-base","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":39.6,"unit":"%","rank":76,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"mixtral-8x7b","modelName":"Mixtral 8x7B","provider":"Mistral AI","rawName":"Mixtral-8x7B-Instruct-v0.1","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":39.6,"unit":"%","rank":76,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"codellama-13b","modelName":"CodeLlama-13B","provider":"Meta","rawName":"CodeLlama-13B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":38.4,"unit":"%","rank":78,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"starcoder-2-15b","modelName":"StarCoder 2 15B","provider":"Hugging Face","rawName":"StarCoder2-15B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":37.8,"unit":"%","rank":79,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"solar-10-7b-instruct-v1-0","modelName":"solar-10.7b-instruct-v1.0","provider":"upstage","rawName":"SOLAR-10.7B-Instruct-v1.0","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":37.2,"unit":"%","rank":80,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"mistral-7b-v0-2","modelName":"Mistral 7B v0.2","provider":"Mistral AI","rawName":"Mistral-7B-Instruct-v0.2","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":36,"unit":"%","rank":81,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"codellama-7b","modelName":"CodeLlama-7B","provider":"Meta","rawName":"CodeLlama-7B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":35.4,"unit":"%","rank":82,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"gemma-1-1-7b-it","modelName":"gemma-1.1-7b-it","provider":"Google","rawName":"gemma-1.1-7b-it","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":35.4,"unit":"%","rank":82,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"xdan-l1-chat-rl-v1-7b","modelName":"xDAN-L1-Chat-RL-v1-7B","provider":null,"rawName":"xDAN-L1-Chat-RL-v1-7B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":32.9,"unit":"%","rank":84,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"python-code-13b","modelName":"Python-Code-13B","provider":null,"rawName":"Python-Code-13B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":30.5,"unit":"%","rank":85,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"starcoder-2-7b","modelName":"StarCoder 2 7B","provider":"Hugging Face","rawName":"StarCoder2-7B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":29.9,"unit":"%","rank":86,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"llama3-8b-base","modelName":"Llama3-8B-base","provider":"Meta","rawName":"Llama3-8B-base","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":29.3,"unit":"%","rank":87,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"starcoder-15b","modelName":"StarCoder-15B","provider":"BigCode","rawName":"StarCoder-15B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":29.3,"unit":"%","rank":87,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"gemma-7b","modelName":"Gemma 7B","provider":"Google","rawName":"gemma-7b","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":28.7,"unit":"%","rank":89,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"codegen-16b","modelName":"CodeGen-16B","provider":null,"rawName":"CodeGen-16B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":28,"unit":"%","rank":90,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"starcoder-2-3b","modelName":"StarCoder 2 3B","provider":"Hugging Face","rawName":"StarCoder2-3B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":27.4,"unit":"%","rank":91,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"codet5-16b","modelName":"CodeT5+-16B","provider":null,"rawName":"CodeT5+-16B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":26.8,"unit":"%","rank":92,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"codegen-6b","modelName":"CodeGen-6B","provider":null,"rawName":"CodeGen-6B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":25.6,"unit":"%","rank":93,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"deepseek-coder-1-3b","modelName":"DeepSeek Coder 1.3B","provider":"DeepSeek","rawName":"DeepSeek-Coder-1.3B-base","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":25.6,"unit":"%","rank":93,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"stable-code-3b","modelName":"stable-code-3B","provider":null,"rawName":"stable-code-3B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":25.6,"unit":"%","rank":93,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"gemma-7b-it","modelName":"gemma-7b-it","provider":"Google","rawName":"gemma-7b-it","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":25,"unit":"%","rank":96,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"codet5-6b","modelName":"CodeT5+-6B","provider":null,"rawName":"CodeT5+-6B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":24.4,"unit":"%","rank":97,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"mistral-7b","modelName":"Mistral-7B","provider":"Mistral AI","rawName":"Mistral-7B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":23.8,"unit":"%","rank":98,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"zephyr-7b","modelName":"Zephyr β-7B","provider":"Hugging Face","rawName":"Zephyr β-7B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":23.2,"unit":"%","rank":99,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"codegen-2b","modelName":"CodeGen-2B","provider":null,"rawName":"CodeGen-2B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":22.6,"unit":"%","rank":100,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"codet5-2b","modelName":"CodeT5+-2B","provider":null,"rawName":"CodeT5+-2B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":22,"unit":"%","rank":101,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"starcoderbase-7b","modelName":"StarCoderBase-7B","provider":"BigCode","rawName":"StarCoderBase-7B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":21.3,"unit":"%","rank":102,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"codegemma-2b","modelName":"codegemma-2b","provider":"Google","rawName":"codegemma-2b","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":20.7,"unit":"%","rank":103,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"gemma-2b","modelName":"Gemma 2B","provider":"Google","rawName":"gemma-2b","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":20.7,"unit":"%","rank":103,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"codegen2-7b","modelName":"CodeGen2-7B","provider":null,"rawName":"CodeGen2-7B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":17.7,"unit":"%","rank":105,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"gemma-1-1-2b-it","modelName":"gemma-1.1-2b-it","provider":"Google","rawName":"gemma-1.1-2b-it","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":17.7,"unit":"%","rank":105,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"codegen2-16b","modelName":"CodeGen2-16B","provider":null,"rawName":"CodeGen2-16B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":16.5,"unit":"%","rank":107,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"starcoderbase-3b","modelName":"StarCoderBase-3B","provider":"BigCode","rawName":"StarCoderBase-3B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":15.9,"unit":"%","rank":108,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"vicuna-13b","modelName":"Vicuna-13B","provider":"LMSYS","rawName":"Vicuna-13B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":15.9,"unit":"%","rank":108,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"gemma-2b-it","modelName":"gemma-2b-it","provider":"Google","rawName":"gemma-2b-it","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":15.2,"unit":"%","rank":110,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"santacoder-1-1b","modelName":"SantaCoder-1.1B","provider":null,"rawName":"SantaCoder-1.1B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":14,"unit":"%","rank":111,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"codegen2-3b","modelName":"CodeGen2-3B","provider":null,"rawName":"CodeGen2-3B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":12.8,"unit":"%","rank":112,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"incoder-6-7b","modelName":"InCoder-6.7B","provider":null,"rawName":"InCoder-6.7B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":12.2,"unit":"%","rank":113,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"starcoderbase-1b","modelName":"StarCoderBase-1B","provider":"BigCode","rawName":"StarCoderBase-1B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":12.2,"unit":"%","rank":113,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"vicuna-7b","modelName":"vicuna-7b","provider":"LMSYS","rawName":"Vicuna-7B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":11.6,"unit":"%","rank":115,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"gpt-j-6b","modelName":"GPT-J-6B","provider":"EleutherAI","rawName":"GPT-J-6B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":11,"unit":"%","rank":116,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"incoder-1-3b","modelName":"InCoder-1.3B","provider":null,"rawName":"InCoder-1.3B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":11,"unit":"%","rank":116,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"codegen2-1b","modelName":"CodeGen2-1B","provider":null,"rawName":"CodeGen2-1B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":9.1,"unit":"%","rank":118,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"gpt-neo-2-7b","modelName":"GPT-Neo-2.7B","provider":"EleutherAI","rawName":"GPT-Neo-2.7B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":6.7,"unit":"%","rank":119,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"polycoder-2-7b","modelName":"PolyCoder-2.7B","provider":null,"rawName":"PolyCoder-2.7B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":6.1,"unit":"%","rank":120,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"stablelm-7b","modelName":"StableLM-7B","provider":null,"rawName":"StableLM-7B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":2.4,"unit":"%","rank":121,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"zyte-1b","modelName":"zyte-1B","provider":null,"rawName":"zyte-1B","variant":"humaneval-plus","setting":"HumanEval+ (extended tests), pass@1 greedy","score":1.8,"unit":"%","rank":122,"rankComputedBySite":true,"date":"2024-12-26","sourceType":"official","source":"evalplus","sourceUrl":"https://evalplus.github.io/leaderboard.html","collected":"2026-10-10"}]}