multimodal benchmark
VideoMMMU
Video-MMMU evaluates Large Multimodal Models' ability to acquire knowledge from expert-level professional videos across six disciplines through three cognitive stages: perception, comprehension, and adaptation. Contains 300 videos and 900 human-annotated questions spanning Art, Business, Science, Medicine, Humanities, and Engineering.
Updated Aug 7, 2026
Published models26
Registry coverage26
MetricScore
EvidenceB
VideoMMMU 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.
VideoMMMU highlights
The top published results on this benchmark's own scale.
What is VideoMMMU?
Definition and scoring fields from the benchmark registry.
Video-MMMU evaluates Large Multimodal Models' ability to acquire knowledge from expert-level professional videos across six disciplines through three cognitive stages: perception, comprehension, and adaptation. Contains 300 videos and 900 human-annotated questions spanning Art, Business, Science, Medicine, Humanities, and Engineering.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- VideoMMMU
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- videommmu|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about VideoMMMU.
Which model scores highest on VideoMMMU?
Gemini 3 Pro is currently ranked first with 87.6%.
What does VideoMMMU measure?
Video-MMMU evaluates Large Multimodal Models' ability to acquire knowledge from expert-level professional videos across six disciplines through three cognitive stages: perception, comprehension, and adaptation. Contains 300 videos and 900 human-annotated questions spanning Art, Business, Science, Medicine, Humanities, and Engineering.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
26 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.