multimodal benchmark
MMMUval
Validation set for MMMU (Massive Multi-discipline Multimodal Understanding and Reasoning) benchmark, designed to evaluate multimodal models on massive multi-discipline tasks demanding college-level subject knowledge and deliberate reasoning across Art & Design, Business, Science, Health & Medicine, Humanities & Social Science, and Tech & Engineering.
Updated Aug 11, 2026
Models4
Model coverage4
MetricScore
EvidenceB
MMMUval Ranking
Higher score ranks better on this benchmark.
| 01 | AC | 80.6% | 100.0% | 4 | C | |
| 02 | AC | 78.7% | 66.7% | 4 | C | |
| 03 | AN | 77.8% | 33.3% | 4 | C | |
| 04 | AC | 64.5% | 0.0% | 4 | C |
MMMUval Score Distribution
A closer view of the leading scores on this benchmark.
MMMUval Highlights
The leading models and scores on this benchmark.
What is MMMUval?
What MMMUval measures and how its scores work.
Validation set for MMMU (Massive Multi-discipline Multimodal Understanding and Reasoning) benchmark, designed to evaluate multimodal models on massive multi-discipline tasks demanding college-level subject knowledge and deliberate reasoning across Art & Design, Business, Science, Health & Medicine, Humanities & Social Science, and Tech & Engineering.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- MMMUval
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- mmmuval|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about MMMUval.
Which model scores highest on MMMUval?
Qwen3 VL 235B A22B Thinking is currently ranked first with 80.6%.
What does MMMUval measure?
Validation set for MMMU (Massive Multi-discipline Multimodal Understanding and Reasoning) benchmark, designed to evaluate multimodal models on massive multi-discipline tasks demanding college-level subject knowledge and deliberate reasoning across Art & Design, Business, Science, Health & Medicine, Humanities & Social Science, and Tech & Engineering.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
4 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.