| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Video Question Answering | VideoMMMU | Accuracy74.9 | 124 | |
| Video Multimodal Understanding | VideoMMMU | Accuracy79.4 | 47 | |
| Video Understanding | VideoMMMU | Accuracy61.2 | 32 | |
| Open World Video Understanding | VideoMMMU | Average Accuracy71.2 | 19 | |
| Professional-level Knowledge Acquisition | VideoMMMU | Accuracy83.6 | 13 | |
| Long Video Reasoning | VideoMMMU | Overall Score61.2 | 8 | |
| Multimodal Video Understanding | VideoMMMU | Overall Score61.2 | 7 | |
| Knowledge Acquisition | VideoMMMU | Delta Knowledge17.2 | 5 |