| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Video Understanding | LongVideo | Accuracy62.75 | 21 | |
| Long-form Video-Language Understanding | LongVideo | Score62.1 | 19 | |
| Long-context Video Understanding | LongVideo (val) | Score62.8 | 7 | |
| Long-context Video Understanding | LongVideo Sub (val) | Score60.9 | 4 |