| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Long Video Understanding | LongVideoBench | Score58.9 | 290 | |
| Long Video Understanding | LongVideoBench (val) | Accuracy80 | 282 | |
| Video Question-Answering | LongVideoBench | Accuracy77.6 | 224 | |
| Long-form Video Understanding | LongVideoBench | Accuracy82.3 | 135 | |
| Video Understanding | LongVideoBench | Accuracy73.89 | 128 | |
| Video Question Answering | LongVideoBench (val) | Accuracy83 | 113 | |
| Long Video Understanding | LongVideoBench | Accuracy80.3 | 103 | |
| Video Understanding | LongVideoBench | Accuracy66.7 | 59 | |
| Video Understanding | LongVideoBench 1-60min | Accuracy56.8 | 49 | |
| Video Understanding | LongVideoBench | Overall Accuracy66.9 | 46 | |
| Video Question Answering | LongVideoBench (LVB) 58 (test) | Accuracy66.42 | 45 | |
| Video Question Answering | LongVideoBench (test) | Accuracy (Long)63.7 | 42 | |
| Long-context video understanding | LongVideoBench (test) | Accuracy66.7 | 28 | |
| Video Understanding | LongVideoBench (test) | Accuracy (Overall)82.3 | 25 | |
| Long-video understanding | LongVideoBench | Average Performance66.7 | 24 | |
| Long Video Understanding | LongVideoBench | LongVideoBench Score57.1 | 24 | |
| Video Question Answering | LONGVIDEOBENCH Medium | Accuracy56.1 | 24 | |
| General Video Understanding | LongVideoBench | Accuracy60.5 | 24 | |
| Video Reasoning | LongVideoBench | LongVideoBench Score59 | 24 | |
| Long-video understanding | LongVideoBench (LVB) (test) | LVB Score67.1 | 22 | |
| Long-video understanding | LongVideoBench (LVB) | Accuracy76.8 | 21 | |
| Video Question Answering | LongVideoBench KFS-Bench (full set) | Accuracy65.5 | 20 | |
| Long-form Video Understanding | LongVideoBench | Overall Score60.4 | 19 | |
| Video Question Answering | LongVideoBench (standard) | Accuracy76.7 | 19 | |
| Long Video Understanding | LongVideoBench 23sec-60 min | Accuracy74.4 | 19 |