| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Video Question Answering | PerceptionTest | Accuracy78.6 | 31 | |
| Video Question Answering | PerceptionTest (val) | Validation Score66.9 | 17 | |
| Video Understanding | PerceptionTest (val) | Accuracy60.4 | 6 | |
| Video Multi-modal Understanding | PerceptionTest | Accuracy62.3 | 4 | |
| Perception and Reasoning | PerceptionTest | Accuracy66.9 | 3 |