multimodal benchmark
MMMU-Pro
A more robust multi-discipline multimodal understanding benchmark that enhances MMMU through a three-step process: filtering text-only answerable questions, augmenting candidate options, and introducing vision-only input settings. Achieves significantly lower model performance (16.8-26.9%) compared to original MMMU, providing more rigorous evaluation that closely mimics real-world scenarios.
Updated Aug 7, 2026
Published models65
Registry coverage65
MetricScore
EvidenceB
MMMU-Pro leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
Score distribution
Top published rows on the benchmark's original scale.
MMMU-Pro highlights
The top published results on this benchmark's own scale.
What is MMMU-Pro?
Definition and scoring fields from the benchmark registry.
A more robust multi-discipline multimodal understanding benchmark that enhances MMMU through a three-step process: filtering text-only answerable questions, augmenting candidate options, and introducing vision-only input settings. Achieves significantly lower model performance (16.8-26.9%) compared to original MMMU, providing more rigorous evaluation that closely mimics real-world scenarios.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- MMMU-Pro
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- mmmu-pro|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about MMMU-Pro.
Which model scores highest on MMMU-Pro?
Gemini 3.5 Flash is currently ranked first with 83.6%.
What does MMMU-Pro measure?
A more robust multi-discipline multimodal understanding benchmark that enhances MMMU through a three-step process: filtering text-only answerable questions, augmenting candidate options, and introducing vision-only input settings. Achieves significantly lower model performance (16.8-26.9%) compared to original MMMU, providing more rigorous evaluation that closely mimics real-world scenarios.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
65 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.