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
MMMU
MMMU (Massive Multi-discipline Multimodal Understanding) is a benchmark designed to evaluate multimodal models on college-level subject knowledge and deliberate reasoning. Contains 11.5K meticulously collected multimodal questions from college exams, quizzes, and textbooks, covering six core disciplines: Art & Design, Business, Science, Health & Medicine, Humanities & Social Science, and Tech & Engineering across 30 subjects and 183 subfields.
Evaluation context and evidence
- Source
- LLM Stats
- Publisher
- IN.AI Research
- Benchmark release
- 2023-11-27
- Collected
- 2026-08-17
- Modality
- multimodal
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.
Original sources
Reported results 63
Shown in source observation order, not ranked. Dates retain the precision provided by the source.
| Model | Value | Unit | Protocol | Reported date and basis | Source |
|---|---|---|---|---|---|
| Qwen3.6 Plus | 0.86 | Not recorded | Not recorded | 2026-04-02 · model_announcement | LLM Stats |
| GPT-5.1 | 0.854 | Not recorded | Not recorded | 2025-11-13 · model_announcement | LLM Stats |
| GPT-5.1 Thinking | 0.854 | Not recorded | Not recorded | 2025-11-12 · model_announcement | LLM Stats |
| GPT-5.1 Instant | 0.854 | Not recorded | Not recorded | 2025-11-12 · model_announcement | LLM Stats |
| GPT-5 | 0.842 | Not recorded | Not recorded | 2025-08-07 · model_announcement | LLM Stats |
| Qwen3.5-122B-A10B | 0.839 | Not recorded | Not recorded | 2026-02-24 · model_announcement | LLM Stats |
| Qwen3.6-27B | 0.829 | Not recorded | Not recorded | 2026-04-21 · model_announcement | LLM Stats |
| o3 | 0.829 | Not recorded | Not recorded | 2025-04-16 · model_announcement | LLM Stats |
| Qwen3.5-27B | 0.823 | Not recorded | Not recorded | 2026-02-24 · model_announcement | LLM Stats |
| Gemini 2.5 Pro Preview 06-05 | 0.82 | Not recorded | Not recorded | 2025-06-05 · model_announcement | LLM Stats |
| Qwen3.6-35B-A3B | 0.817 | Not recorded | Not recorded | 2026-04-16 · model_announcement | LLM Stats |
| o4-mini | 0.816 | Not recorded | Not recorded | 2025-04-16 · model_announcement | LLM Stats |
| Qwen3.5-35B-A3B | 0.814 | Not recorded | Not recorded | 2026-02-24 · model_announcement | LLM Stats |
| Gemini 2.5 Flash | 0.797 | Not recorded | Not recorded | 2025-05-20 · model_announcement | LLM Stats |
| Gemini 2.5 Pro | 0.796 | Not recorded | Not recorded | 2025-05-20 · model_announcement | LLM Stats |
| Step3-VL-10B | 0.781 | Not recorded | Not recorded | 2026-01-15 · model_announcement | LLM Stats |
| Grok-3 | 0.78 | Not recorded | Not recorded | 2025-02-17 · model_announcement | LLM Stats |
| o1 | 0.776 | Not recorded | Not recorded | 2024-12-17 · model_announcement | LLM Stats |
| Gemini 2.0 Flash Thinking | 0.754 | Not recorded | Not recorded | 2025-01-21 · model_announcement | LLM Stats |
| GPT-4.5 | 0.752 | Not recorded | Not recorded | 2025-02-27 · model_announcement | LLM Stats |
| Command A+ | 0.751 | Not recorded | Not recorded | 2026-05-20 · model_announcement | LLM Stats |
| Claude 3.7 Sonnet | 0.75 | Not recorded | Not recorded | 2025-02-24 · model_announcement | LLM Stats |
| GPT-4.1 | 0.748 | Not recorded | Not recorded | 2025-04-14 · model_announcement | LLM Stats |
| Claude Sonnet 4 | 0.744 | Not recorded | Not recorded | 2025-05-22 · model_announcement | LLM Stats |
| Llama 4 Maverick | 0.734 | Not recorded | Not recorded | 2025-04-05 · model_announcement | LLM Stats |
| Gemini 2.5 Flash-Lite | 0.729 | Not recorded | Not recorded | 2025-06-17 · model_announcement | LLM Stats |
| GPT-4.1 mini | 0.727 | Not recorded | Not recorded | 2025-04-14 · model_announcement | LLM Stats |
| GPT-4o | 0.722 | Not recorded | Not recorded | 2024-08-06 · model_announcement | LLM Stats |
| Gemini 2.0 Flash | 0.707 | Not recorded | Not recorded | 2024-12-01 · model_announcement | LLM Stats |
| QvQ-72B-Preview | 0.703 | Not recorded | Not recorded | 2024-12-25 · model_announcement | LLM Stats |
| Qwen2.5 VL 72B Instruct | 0.702 | Not recorded | Not recorded | 2025-01-26 · model_announcement | LLM Stats |
| Qwen2.5 VL 32B Instruct | 0.7 | Not recorded | Not recorded | 2025-02-28 · model_announcement | LLM Stats |
| Kimi-k1.5 | 0.7 | Not recorded | Not recorded | 2025-01-20 · model_announcement | LLM Stats |
| Llama 4 Scout | 0.694 | Not recorded | Not recorded | 2025-04-05 · model_announcement | LLM Stats |
| Claude 3.5 Sonnet | 0.683 | Not recorded | Not recorded | 2024-10-22 · model_announcement | LLM Stats |
| Gemini 2.0 Flash-Lite | 0.68 | Not recorded | Not recorded | 2025-02-05 · model_announcement | LLM Stats |
| Grok-2 | 0.661 | Not recorded | Not recorded | 2024-08-13 · model_announcement | LLM Stats |
| Gemini 1.5 Pro | 0.659 | Not recorded | Not recorded | 2024-05-01 · model_announcement | LLM Stats |
| Pixtral Large | 0.64 | Not recorded | Not recorded | 2024-11-18 · model_announcement | LLM Stats |
| Grok-2 mini | 0.632 | Not recorded | Not recorded | 2024-08-13 · model_announcement | LLM Stats |
| Mistral Small 3.2 24B Instruct | 0.625 | Not recorded | Not recorded | 2025-06-20 · model_announcement | LLM Stats |
| Gemini 1.5 Flash | 0.623 | Not recorded | Not recorded | 2024-05-01 · model_announcement | LLM Stats |
| Nova Pro | 0.617 | Not recorded | Not recorded | 2024-11-20 · model_announcement | LLM Stats |
| Llama 3.2 90B Instruct | 0.603 | Not recorded | Not recorded | 2024-09-25 · model_announcement | LLM Stats |
| GPT-4o mini | 0.594 | Not recorded | Not recorded | 2024-07-18 · model_announcement | LLM Stats |
| Mistral Small 3.1 24B Base | 0.5927 | Not recorded | Not recorded | 2025-03-17 · model_announcement | LLM Stats |
| Mistral Small 3.1 24B Instruct | 0.5927 | Not recorded | Not recorded | 2025-03-17 · model_announcement | LLM Stats |
| Qwen2.5-Omni-7B | 0.592 | Not recorded | Not recorded | 2025-03-27 · model_announcement | LLM Stats |
| Qwen2.5 VL 7B Instruct | 0.586 | Not recorded | Not recorded | 2025-01-26 · model_announcement | LLM Stats |
| Nova Lite | 0.562 | Not recorded | Not recorded | 2024-11-20 · model_announcement | LLM Stats |
| GPT-4.1 nano | 0.554 | Not recorded | Not recorded | 2025-04-14 · model_announcement | LLM Stats |
| Phi-4-multimodal-instruct | 0.551 | Not recorded | Not recorded | 2025-02-01 · model_announcement | LLM Stats |
| Gemini 1.5 Flash 8B | 0.537 | Not recorded | Not recorded | 2024-03-15 · model_announcement | LLM Stats |
| Grok-1.5V | 0.536 | Not recorded | Not recorded | 2024-04-12 · model_announcement | LLM Stats |
| Grok-1.5 | 0.536 | Not recorded | Not recorded | 2024-03-28 · model_announcement | LLM Stats |
| Pixtral-12B | 0.525 | Not recorded | Not recorded | 2024-09-17 · model_announcement | LLM Stats |
| DeepSeek VL2 | 0.511 | Not recorded | Not recorded | 2024-12-13 · model_announcement | LLM Stats |
| Llama 3.2 11B Instruct | 0.507 | Not recorded | Not recorded | 2024-09-25 · model_announcement | LLM Stats |
| DeepSeek VL2 Small | 0.48 | Not recorded | Not recorded | 2024-12-13 · model_announcement | LLM Stats |
| Gemini 1.0 Pro | 0.479 | Not recorded | Not recorded | 2024-02-15 · model_announcement | LLM Stats |
| Phi-3.5-vision-instruct | 0.43 | Not recorded | Not recorded | 2024-08-23 · model_announcement | LLM Stats |
| DeepSeek VL2 Tiny | 0.407 | Not recorded | Not recorded | 2024-12-13 · model_announcement | LLM Stats |
| GPT-3.5 Turbo | 0.0 | Not recorded | Not recorded | 2023-03-21 · model_announcement | LLM Stats |