| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Video Question Answering | VideoTemp-Bench (Overall) | Accuracy84.7 | 6 | |
| Temporal Grounding | VideoTemp-Bench (Overall) | mIoU34 | 6 | |
| Video Question Answering | VideoTemp-Bench >20min | Accuracy76.1 | 6 | |
| Temporal Grounding | VideoTemp-Bench >20min | mIoU14.8 | 6 | |
| Video Question Answering | VideoTemp-Bench 10~20min | Accuracy90 | 6 | |
| Temporal Grounding | VideoTemp-Bench 10~20min | mIoU36.1 | 6 | |
| Video Question Answering | VideoTemp-Bench 3~10min | Accuracy91.3 | 6 | |
| Temporal Grounding | VideoTemp-Bench 3~10min | mIoU46.1 | 6 | |
| Video Question Answering | VideoTemp-Bench 0~3min | Accuracy82 | 6 | |
| Temporal Grounding | VideoTemp-Bench (0~3min) | mIoU39.1 | 6 |