AI benchmarks and leaderboards are different things
Learn the difference between a benchmark, an evaluation run and a leaderboard, and use each to answer the right question.
LLM Stats
Multilingual Massive Multitask Language Understanding dataset released by OpenAI, featuring professionally translated MMLU test questions across 14 languages including Arabic, Bengali, German, Spanish, French, Hindi, Indonesian, Italian, Japanese, Korean, Portuguese, Swahili, Yoruba, and Chinese. Contains approximately 15,908 multiple-choice questions per language covering 57 subjects.
These are source-reported observations, not independent reruns by this site. Check the task version, evaluation protocol, unit and reporting date before comparing models. Results from different setups are not a universal ranking.
Shown in source observation order, not ranked. Dates retain the precision provided by the source.
| Model | Value | Unit | Protocol | Reported date and basis | Source |
|---|---|---|---|---|---|
| Claude Mythos Preview | 0.927 | Not recorded | Not recorded | 2026-04-07 · model_announcement | LLM Stats |
| Gemini 3.1 Pro | 0.926 | Not recorded | Not recorded | 2026-02-19 · model_announcement | LLM Stats |
| Gemini 3 Flash | 0.918 | Not recorded | Not recorded | 2025-12-17 · model_announcement | LLM Stats |
| Gemini 3 Pro | 0.918 | Not recorded | Not recorded | 2025-11-18 · model_announcement | LLM Stats |
| Claude Opus 4.7 | 0.915 | Not recorded | Not recorded | 2026-04-16 · model_announcement | LLM Stats |
| Claude Opus 4.6 | 0.911 | Not recorded | Not recorded | 2026-02-05 · model_announcement | LLM Stats |
| Claude Opus 4.5 | 0.908 | Not recorded | Not recorded | 2025-11-24 · model_announcement | LLM Stats |
| Qwen3.7 Max | 0.903 | Not recorded | Not recorded | 2026-05-19 · model_announcement | LLM Stats |
| GPT-5.2 | 0.896 | Not recorded | Not recorded | 2025-12-11 · model_announcement | LLM Stats |
| Qwen3.6 Plus | 0.895 | Not recorded | Not recorded | 2026-04-02 · model_announcement | LLM Stats |
| Claude Opus 4.1 | 0.895 | Not recorded | Not recorded | 2025-08-05 · model_announcement | LLM Stats |
| Claude Sonnet 4.6 | 0.893 | Not recorded | Not recorded | 2026-02-17 · model_announcement | LLM Stats |
| Claude Sonnet 4.5 | 0.891 | Not recorded | Not recorded | 2025-09-29 · model_announcement | LLM Stats |
| Qwen3.7-Plus | 0.89 | Not recorded | Not recorded | 2026-05-31 · model_announcement | LLM Stats |
| Gemini 3.1 Flash-Lite | 0.889 | Not recorded | Not recorded | 2026-03-03 · model_announcement | LLM Stats |
| Claude Opus 4 | 0.888 | Not recorded | Not recorded | 2025-05-22 · model_announcement | LLM Stats |
| Qwen3.5-397B-A17B | 0.885 | Not recorded | Not recorded | 2026-02-16 · model_announcement | LLM Stats |
| Gemma 4 31B | 0.884 | Not recorded | Not recorded | 2026-04-02 · model_announcement | LLM Stats |
| o1 | 0.877 | Not recorded | Not recorded | 2024-12-17 · model_announcement | LLM Stats |
| GPT-4.1 | 0.873 | Not recorded | Not recorded | 2025-04-14 · model_announcement | LLM Stats |
| Qwen3.5-122B-A10B | 0.867 | Not recorded | Not recorded | 2026-02-24 · model_announcement | LLM Stats |
| Qwen3 235B A22B | 0.867 | Not recorded | Not recorded | 2025-04-29 · model_announcement | LLM Stats |
| Claude Sonnet 4 | 0.865 | Not recorded | Not recorded | 2025-05-22 · model_announcement | LLM Stats |
| Gemma 4 26B-A4B | 0.863 | Not recorded | Not recorded | 2026-04-02 · model_announcement | LLM Stats |
| Claude 3.7 Sonnet | 0.861 | Not recorded | Not recorded | 2025-02-24 · model_announcement | LLM Stats |
| Qwen3.5-27B | 0.859 | Not recorded | Not recorded | 2026-02-24 · model_announcement | LLM Stats |
| K-EXAONE-236B-A23B | 0.857 | Not recorded | Not recorded | 2025-12-31 · model_announcement | LLM Stats |
| Mistral Large 3 (675B Base) | 0.855 | Not recorded | Not recorded | 2025-12-04 · model_announcement | LLM Stats |
| Mistral Large 3 (675B Instruct 2512 Eagle) | 0.855 | Not recorded | Not recorded | 2025-12-04 · model_announcement | LLM Stats |
| Mistral Large 3 (675B Instruct 2512) | 0.855 | Not recorded | Not recorded | 2025-12-04 · model_announcement | LLM Stats |
| Mistral Large 3 (675B Instruct 2512 NVFP4) | 0.855 | Not recorded | Not recorded | 2025-12-04 · model_announcement | LLM Stats |
| Qwen3.5-35B-A3B | 0.852 | Not recorded | Not recorded | 2026-02-24 · model_announcement | LLM Stats |
| GPT-4.5 | 0.851 | Not recorded | Not recorded | 2025-02-27 · model_announcement | LLM Stats |
| GPT OSS 120B High | 0.838 | Not recorded | Not recorded | 2025-08-05 · model_announcement | LLM Stats |
| Gemma 4 12B | 0.834 | Not recorded | Not recorded | 2026-05-23 · model_announcement | LLM Stats |
| Claude Haiku 4.5 | 0.83 | Not recorded | Not recorded | 2025-10-15 · model_announcement | LLM Stats |
| DiffusionGemma 26B-A4B | 0.815 | Not recorded | Not recorded | 2026-06-10 · model_announcement | LLM Stats |
| GPT-4o | 0.814 | Not recorded | Not recorded | 2024-08-06 · model_announcement | LLM Stats |
| Qwen3.5-9B | 0.812 | Not recorded | Not recorded | 2026-03-02 · model_announcement | LLM Stats |
| GPT-4.1 mini | 0.785 | Not recorded | Not recorded | 2025-04-14 · model_announcement | LLM Stats |
| Gemma 4 E4B | 0.766 | Not recorded | Not recorded | 2026-04-02 · model_announcement | LLM Stats |
| Qwen3.5-4B | 0.761 | Not recorded | Not recorded | 2026-03-02 · model_announcement | LLM Stats |
| Mistral Large 3 | 0.742 | Not recorded | Not recorded | 2025-09-01 · model_announcement | LLM Stats |
| Phi-3.5-MoE-instruct | 0.699 | Not recorded | Not recorded | 2024-08-23 · model_announcement | LLM Stats |
| Gemma 4 E2B | 0.674 | Not recorded | Not recorded | 2026-04-02 · model_announcement | LLM Stats |
| GPT-4.1 nano | 0.669 | Not recorded | Not recorded | 2025-04-14 · model_announcement | LLM Stats |
| Qwen3.5-2B | 0.631 | Not recorded | Not recorded | 2026-03-02 · model_announcement | LLM Stats |
| Phi-3.5-mini-instruct | 0.554 | Not recorded | Not recorded | 2024-08-23 · model_announcement | LLM Stats |
| Qwen3.5-0.8B | 0.443 | Not recorded | Not recorded | 2026-03-02 · model_announcement | LLM Stats |