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 11, 2026
Models26
Model coverage26
MetricScore
EvidenceB
VideoMMMU Ranking
Higher score ranks better on this benchmark.
VideoMMMU Score Distribution
A closer view of the leading scores on this benchmark.
VideoMMMU Highlights
The leading models and scores on this benchmark.
What is VideoMMMU?
What VideoMMMU measures and how its scores work.
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. This benchmark is not independently verified and has an evidence level of B.
- Family
- VideoMMMU
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- videommmu|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
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 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.