multimodal benchmark
MMMUval Leaderboard
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 17, 2026
Models4
Model coverage4
MetricScore
EvidenceB
MMMUval Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAC | Score80.6% | Percentile100.0% | Participants4 | EvidenceC | Evaluated |
| Rank02 | ModelAC | Score78.7% | Percentile66.7% | Participants4 | EvidenceC | Evaluated |
| Rank03 | ModelAN | Score77.8% | Percentile33.3% | Participants4 | EvidenceC | Evaluated |
| Rank04 | ModelAC | Score64.5% | Percentile0.0% | Participants4 | EvidenceC | Evaluated |
MMMUval Highlights
The leading models and scores on this benchmark.
MMMUval Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for MMMUval
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis mmmuval AI model leaderboard uses descending score in the benchmark's original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01ACQwen3 VL 235B A22B ThinkingAlibaba Cloud / Qwen Team
- Score
- 80.6%
Strengths
- Ranks #1 of 4 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures MMMUval, not total model capability
- 02ACQwen3 VL 235B A22B InstructAlibaba Cloud / Qwen Team
- Score
- 78.7%
Strengths
- Ranks #2 of 4 compared models
- 67th percentile on this benchmark
- C evidence result
Considerations
- This result measures MMMUval, not total model capability
- 03ANClaude Sonnet 4.5Anthropic
- Score
- 77.8%
- Price
- $3.0 input / $15 output per 1M tokens
- Speed
- Up to 42 tok/s via Anthropic
Strengths
- Ranks #3 of 4 compared models
- 33th percentile on this benchmark
- C evidence result
Considerations
- This result measures MMMUval, not total model capability
- 04ACQwen2-VL-72B-InstructAlibaba Cloud / Qwen Team
- Score
- 64.5%
Strengths
- Ranks #4 of 4 compared models
- 0th percentile on this benchmark
- C evidence result
Considerations
- This result measures MMMUval, not total model capability
Selection summary
Best AI Models for MMMUval
Qwen3 VL 235B A22B Thinking currently leads MMMUval with 80.6%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
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.