← Benchmarks
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.
id videommmu · max 1 · 28 models reported
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro Google | 0.88 |
| 2 | Gemini 3 Flash Google | 0.87 |
| 3 | Kimi K2.5 Moonshot AI · open | 0.87 |
| 4 | GPT-5.2 OpenAI | 0.86 |
| 5 | Qwen3.7-Plus Alibaba Cloud / Qwen Team | 0.85 |