| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Temporal Video Understanding | TVBench (test) | Accuracy51.4 | 22 | |
| Short Video Question Answering | TVBench (test) | Accuracy54.7 | 12 | |
| Short video understanding | TVBench | Accuracy63.6 | 9 | |
| General Video Understanding | TVBench | Accuracy71.5 | 6 | |
| Video Question Answering | TVBench | Accuracy63.5 | 5 | |
| Complex Reasoning | TVbench | Accuracy54.7 | 4 |