| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Temporal Spatial Reasoning | VSIBench | Average Accuracy62.9 | 19 | |
| Spatial Understanding | VSIbench | Accuracy68.3 | 16 | |
| Spatial Perception Video Understanding | VsiBench | Overall Score39.8 | 14 | |
| Video Social Intelligence | VSIBench | Accuracy36.1 | 14 | |
| Video Reasoning | VSIBench | Accuracy43.3 | 10 | |
| Video Question Answering | VSIBench | Accuracy45.4 | 8 |