LMArena · GPQA · SWE-bench · HLE · ARC-AGI · OSWorld · BFCL
مقاييس أداء نماذج الذكاء الاصطناعي
3086 نتيجة لـ 1079 نموذجًا على 23 مقياسًا عامًا. كل رقم مرتبط بمصدره، وأرقام الشركات المطوّرة مميّزة.
3086 نتيجة 1079 نموذجًا 23 مقياسًا حُدّث في 22 أكتوبر 2026
Current champions
The top model on each core benchmark. Only official leaderboards, independent evaluations and compiled data count; vendor self-reports are excluded.
LMArena Text Gemini 4 Argon 1525 تفضيل بشري GPQA Diamond Gemini 4 Argon 96.4% العلوم Humanity's Last Exam GPT-6 Astra 54.8% المعرفة AIME (OTIS Mock AIME 2024–2025) Gemini 4 Argon 100.0% الرياضيات SWE-bench Verified Claude Opus 4.7 83.5% البرمجة بالوكلاء Terminal-Bench 2.0 GPT-5.5 84.7% البرمجة بالوكلاء OSWorld (Verified) Claude Sonnet 4.6 72.1% استخدام الحاسوب τ²-bench Gemini 3.0 Pro 85.3% الأدوات والوكلاء BFCL v4 (function calling) Claude Opus 4.5 77.5% الأدوات والوكلاء MMLU-Pro Gemini 3.1 Pro 91.2% المعرفة
مصفوفة النماذج × المقاييس
كل خلية هي أفضل نتيجة في الإعداد الرئيسي (الأولوية للترتيبات الرسمية والتقييمات المستقلة). ◇ = رقم من الشركة أو ورقة بحثية فقط. انقر على العمود للترتيب وحدّد النماذج للمقارنة.
| النموذج | LMArena Text | GPQA Diamond | Humanity's Last Exam | AIME (OTIS Mock AIME 2024–2025) | SWE-bench Verified | Terminal-Bench 2.0 | OSWorld (Verified) | τ²-bench | BFCL v4 (function calling) | MMLU-Pro |
|---|---|---|---|---|---|---|---|---|---|---|
| GPT-5.2OpenAI | 1437 | 91.4% | 27.8% | 96.1% | 73.8% | 64.9% | — | 81.6% | 55.9% | 87.4% ◇ |
| Gemini 3 ProGoogle | 1486 | 92.6% | 37.5% | 91.4% | 77.4% | 69.4% | — | 75.9% | 72.5% | 90.1% ◇ |
| Claude Sonnet 4.5Anthropic | 1456 | 82.3% | 13.7% | 77.8% | 74.8% | 46.5% | 62.9% | 72.4% | 73.2% | — |
| GPT-5OpenAI | 1435 | 86.2% | 25.3% | 91.4% | 74.4% | 49.6% | — | 81.6% | — | 87.1% ◇ |
| o3OpenAI | 1432 | 81.8% | 20.3% | 84.4% | 62.3% | — | 23.0% | 73.9% ◇ | 63.0% | — |
| Claude Opus 4.5Anthropic | 1474 | 86.0% | 25.2% | 86.1% | 79.2% | 63.1% | 66.3% ◇ | 79.6% | 77.5% | — |
| Gemini 2.5 Pro (Jun 2025)Google | 1446 | 85.3% | 21.6% | 84.7% | 57.6% | 32.6% | — | — | — | 86.0% ◇ |
| Claude Sonnet 4Anthropic | 1402 | 79.2% | 7.8% | 68.9% | 76.8% | — | 43.9% | 80.5% ◇ | — | — |
| o4-miniOpenAI | 1391 | 79.6% | 18.1% | 81.7% | 64.6% | — | — | 68.3% | 53.2% | — |
| GPT-4.1OpenAI | 1415 | 66.9% | 5.4% | 38.3% | 48.5% | — | — | 74.0% | 54.0% | 81.8% ◇ |
| Claude 3.7 SonnetAnthropic | 1388 | 79.7% | 8.0% | 57.8% | 66.4% | — | 35.8% | 72.1% | — | 84.0% ◇ |
| Qwen2.5-72BAlibaba (Qwen) | 1303 | 49.1% | — | 8.1% | — | — | 5.0% | — | — | 71.6% ◇ |
| Claude Opus 4.7Anthropic | 1501 | 90.2% | 36.2% | 97.8% | 83.5% | 80.2% | — | — | — | — |
| GPT-5.4OpenAI | 1475 | 93.3% | 36.2% | 97.8% | 76.9% | 81.8% | — | — | — | 87.5% ◇ |
| Gemini 3.1 ProGoogle | 1487 | 94.4% | 46.4% | 95.6% | 75.6% | 80.2% | — | — | — | 91.2% |
| Claude Sonnet 4.6Anthropic | 1472 | 87.4% | — | 85.8% | 75.2% | 53.4% | 72.1% | — | — | — |
| Kimi K2.5Moonshot AI | 1450 | 87.6% | 24.4% | 92.2% | 73.8% | 43.2% | 63.3% | — | — | — |
| GPT-5.1OpenAI | 1456 | 87.6% | 23.7% | 88.6% | 68.0% | 47.6% | — | — | — | 86.4% ◇ |
| GPT-5 miniOpenAI | 1390 | 75.0% | 19.4% | 86.7% | 64.7% | 34.8% | — | — | 55.5% | — |
| Claude Opus 4Anthropic | 1426 | 76.3% | 10.7% | 64.4% | 70.7% | — | — | 81.4% ◇ | — | — |
| Gemini 1.5 Pro (Sept 2024)Google | 1351 | 57.2% | 4.6% | 23.1% | — | — | — | — | — | 70.3% |
| Claude 3.5 SonnetAnthropic | 1374 | 54.0% | — | 6.5% | 63.4% | — | — | — | — | 77.6% |
| GPT-4o (May 2024)OpenAI | 1346 | 48.9% | — | 6.3% | 38.8% | — | — | — | — | 72.5% |
| Claude 3 HaikuAnthropic | 1262 | 36.3% | — | 1.8% | 40.6% | — | — | — | — | 42.3% |
| GPT-4 Turbo (Nov 2023)OpenAI | 1325 | 42.4% | — | — | 22.4% | — | — | — | — | 63.7% |
| GLM-5Zhipu AI (Z.ai) | 1458 | 87.8% | — | 80.0% | 72.8% | 52.4% | — | 73.7% | — | 86.0% ◇ |
| Claude Opus 4.6Anthropic | 1504 | 90.5% | 34.4% | 94.4% | 78.7% | 79.8% | — | — | — | — |
| Gemini 3 FlashGoogle | 1473 | 89.4% | — | 95.6% | 75.8% | 64.3% | — | 76.8% | — | — |
| DeepSeek-V3.2DeepSeek | 1425 | 83.4% | — | 87.8% | 70.0% | 39.5% | — | 81.1% ◇ | — | 85.0% ◇ |
| Claude Haiku 4.5Anthropic | 1414 | 71.2% | — | 66.7% | 66.6% | 35.5% | — | — | 68.7% | — |
| GPT-5 nanoOpenAI | 1337 | 69.4% | — | 81.1% | 34.8% | 21.8% | — | — | 51.5% | — |
| Claude Opus 4.1Anthropic | 1450 | 76.8% | 11.5% | 68.9% | 73.3% | 38.0% | — | 82.4% ◇ | — | — |
| GPT-4.1 miniOpenAI | 1383 | 65.8% | — | 44.7% | 23.9% | — | — | 61.4% | 50.5% | — |
| Phi-4Microsoft Research | 1256 | 56.1% | — | 13.8% | — | — | — | — | 28.8% | 70.4% ◇ |
| Llama 3.3 70BMeta | 1318 | 47.4% | — | 5.1% | — | — | — | — | 31.9% | 65.9% |
| Gemini 1.5 Flash (Sep 2024)Google | 1309 | 47.3% | — | 16.3% | — | — | — | — | — | 64.1% |
| Llama 3.1-8BMeta | 1211 | 27.0% | — | 1.7% | — | — | — | — | 25.8% | 36.6% |
| GPT-4o miniOpenAI | 1318 | 37.7% | — | 6.9% | — | — | — | — | — | 63.1% |
| Claude 3 OpusAnthropic | 1322 | 47.2% | — | 4.7% | 15.8% | — | — | — | — | 68.5% |
| Gemini 3.8 FlashGoogle | 1497 | 95.4% | 44.5% | 98.9% | — | — | — | — | — | — |
كل المقاييس
البرمجة
LMArena WebDevنشط Arena where two models each build a web app from the same prompt and users vote on the result. 127 نموذجًا · الأفضل: 1813 LiveCodeBenchلم يُحدَّث مؤخرًا Coding problems collected continuously from LeetCode, AtCoder and Codeforces with their release dates, so models can be scored only on problems published after their training cut-off. 22 نموذجًا · الأفضل: 75.8% HumanEval / HumanEval+مشبع 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. 122 نموذجًا · الأفضل: 89.0%
عام
Open LLM Leaderboard v2مؤرشف Hugging Face's leaderboard of open-weight models, scored on IFEval, BBH, MATH Lvl 5, GPQA, MuSR and MMLU-Pro with normalised scores. The leaderboard was archived in 2025 and no longer accepts submissions. 294 نموذجًا · الأفضل: 48.0% Artificial Analysis Intelligence Indexرابط فقط Independent composite index that runs a battery of evaluations plus price and speed measurements across API models. رابط فقط
المعرفة
MMLUمشبع About 14,000 multiple-choice questions over 57 subjects, from elementary maths to law and medicine. 158 نموذجًا · الأفضل: 88.1% MMLU-Proنشط Harder successor to MMLU: about 12,000 reasoning-heavy questions in 14 disciplines with 10 answer options. 243 نموذجًا · الأفضل: 91.2% Humanity's Last Examنشط About 2,500 expert-written questions across 100+ subjects from the Center for AI Safety and Scale AI, filtered to stump frontier models at creation time. 46 نموذجًا · الأفضل: 54.8%
البرمجة بالوكلاء
SWE-bench Verifiedمثير للجدل 500 human-validated GitHub issues from 12 Python repositories; the system must produce a patch that makes the hidden tests pass. 81 نموذجًا · الأفضل: 83.5% SWE-bench Proرابط فقط Scale AI's harder, longer-horizon successor to SWE-bench with a 731-task public split and private/commercial splits. رابط فقط Terminal-Bench 2.0نشط Hard, realistic tasks an agent must finish in a sandboxed terminal (Stanford × Laude Institute). 45 نموذجًا · الأفضل: 84.7%
الرياضيات
AIME (OTIS Mock AIME 2024–2025)نشط AIME-style competition maths (integer answers 0–999). We use Epoch AI's runs on the OTIS Mock AIME 2024–2025 papers, which are less exposed than past official AIME papers. 200 نموذجًا · الأفضل: 100.0% MATH Level 5مشبع The hardest (level 5) problems of the MATH competition dataset (Hendrycks et al., 2021). 94 نموذجًا · الأفضل: 98.1%
الاستدلال المجرد
ARC-AGI-1مشبع Abstract grid puzzles (François Chollet) that test learning a new rule from a few examples. 6 نموذجًا · الأفضل: 98.5% ARC-AGI-2نشط Harder second version of ARC-AGI (2025), designed so that brute-force search is not enough. 4 نموذجًا · الأفضل: 95.0% ARC-AGI-3نشط Interactive, game-like third version of ARC-AGI that tests exploration and learning inside novel environments. 3 نموذجًا · الأفضل: 99.9%
استخدام الحاسوب
الأدوات والوكلاء
τ²-benchنشط Sierra's customer-service agent benchmark: the agent follows a policy and uses tools while an LLM-simulated user talks to it (retail, airline, telecom, banking). 43 نموذجًا · الأفضل: 85.3% BFCL v4 (function calling)نشط Berkeley Function Calling Leaderboard: single, parallel and multi-turn tool calls, web search, memory and relevance detection. 80 نموذجًا · الأفضل: 77.5%
الصينية
CMMLUلم يُحدَّث مؤخرًا Chinese multitask knowledge benchmark: 67 subjects including China-specific topics. 12 نموذجًا · الأفضل: 90.3% C-Evalلم يُحدَّث مؤخرًا Chinese evaluation suite of about 13,900 multiple-choice questions over 52 disciplines and four difficulty levels. 11 نموذجًا · الأفضل: 68.7% SuperCLUEرابط فقط Periodic Chinese general-capability evaluation of domestic and international models, published as reports. رابط فقط
طريقة الجمع
- We read official data files and public datasets (Hugging Face, GitHub, CSV downloads) and never invent or estimate scores.
- Model names from different leaderboards are merged into one model page (for example dated versions and reasoning-effort variants).
- Leaderboards that restrict reuse are cited with their top entries only, or linked without copying.
- Data is refreshed by a repeatable script; each run keeps a dated snapshot so changes can be compared over time.
نوع المصدر
- ترتيب رسمي
- The benchmark maintainers' own leaderboard
- تقييم مستقل
- An independent evaluator ran the model itself (e.g. Epoch AI)
- أعلنته الشركة
- Self-reported or submitted by the model developer
- ورقة / تقرير تقني
- Reported in a paper or technical report (usually by the developer)
- تجميع طرف ثالث
- Compiled by Epoch AI; the original source is not given per row
مصادر البيانات والتراخيص
| المصدر | الترخيص / الشروط | طريقة استخدامنا | آخر جلب |
|---|---|---|---|
| LMArena leaderboard dataset LMArena, Arena Leaderboard Dataset (Hugging Face), CC BY 4.0 | CC BY 4.0 | Open licence – full data with attribution | 10 أكتوبر 2026 ⚠︎ |
| Epoch AI Benchmarking Hub Epoch AI, 'Capabilities & benchmarking', https://epoch.ai/benchmarks (CC BY 4.0) | CC BY 4.0 | Open licence – full data with attribution | 22 أكتوبر 2026 |
| SWE-bench leaderboards (swebench.com) SWE-bench team, swebench.com leaderboards | No explicit licence (NOASSERTION) – factual scores only, with citation | No explicit licence – factual scores only, with citation | 22 أكتوبر 2026 |
| LiveCodeBench leaderboard LiveCodeBench (Jain et al.), livecodebench.github.io | No explicit licence on the site repo (benchmark code MIT) – factual scores only, with citation | No explicit licence – factual scores only, with citation | 22 أكتوبر 2026 |
| EvalPlus leaderboard EvalPlus team, evalplus.github.io | Apache-2.0 (site repo) | Open licence – full data with attribution | 22 أكتوبر 2026 |
| Berkeley Function Calling Leaderboard (BFCL) Gorilla / BFCL team, UC Berkeley | Apache-2.0 (gorilla repo) | Open licence – full data with attribution | 22 أكتوبر 2026 |
| τ²-bench leaderboard submissions Sierra Research, τ²-bench | MIT (repo) | Open licence – full data with attribution | 22 أكتوبر 2026 |
| MMLU-Pro leaderboard (TIGER-Lab) TIGER-Lab, MMLU-Pro leaderboard | Apache-2.0 (dataset) | Open licence – full data with attribution | 22 أكتوبر 2026 |
| Hugging Face Open LLM Leaderboard v2 (archived) Hugging Face, Open LLM Leaderboard (archived 2025) | No licence tag – factual scores only, with citation | No explicit licence – factual scores only, with citation 4576 rows in archive; 353 official-developer models kept | 22 أكتوبر 2026 |
| ARC Prize leaderboard ARC Prize Foundation, arcprize.org/leaderboard | ARC Prize Terms: no copying/aggregation for commercial purposes without permission | Restricted – only top entries cited top 10 per set only (terms) | 22 أكتوبر 2026 |
| CMMLU leaderboard (GitHub README) Li et al., CMMLU (CC BY-NC-SA 4.0) | CC BY-NC-SA 4.0 | Restricted – only top entries cited | 22 أكتوبر 2026 |
| C-Eval (GitHub README, initial release table) Huang et al., C-Eval | Code MIT; dataset CC BY-NC-SA 4.0 | Restricted – only top entries cited | 22 أكتوبر 2026 |
| Artificial Analysis Artificial Analysis | Free API requires an API key and attribution; no open bulk data | Not collected – link only | — |
| SuperCLUE CLUE / SuperCLUE | No open data interface | Not collected – link only | — |
| Scale AI SEAL leaderboards (SWE-bench Pro, HLE) Scale AI | No open data interface | Not collected – link only | — |
لوكلاء الذكاء الاصطناعي
The same data as JSON: benchmark metadata with licences, every model's best scores and per-benchmark result lists with source links.
/api/benchmarks.json/api/benchmarks/matrix.json/api/benchmarks/<id>.json/llms.txt