| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Long Video Understanding | LVBench | Accuracy74.8 | 133 | |
| Video Question-Answering | LVBench | Accuracy84.1 | 108 | |
| Video Understanding | LVBench | Average Score73.5 | 67 | |
| Long-video understanding | LVBench (test) | LVBench Score71.8 | 43 | |
| Long-Form Video Understanding | LVBench | Overall Score49.4 | 35 | |
| Video Question Answering | LVBench | Overall Score60.7 | 32 | |
| Extremely long-video understanding | LVBench | Score78.7 | 25 | |
| Video Reasoning | LVBench | LVBench Score43.3 | 24 | |
| Video Understanding | LVBench (test) | Accuracy77 | 21 | |
| Video Question Answering | LVBench (val) | Score51 | 16 | |
| Video Understanding | LVbench | MAT12.12 | 16 | |
| Long Video Understanding | LVBench (val) | Score58.7 | 15 | |
| Video Question Answering | LVBench (test) | Accuracy48.9 | 14 | |
| Exocentric Video Understanding | LVBench | Score56.5 | 13 | |
| Long-video Understanding | LVBench 1.0 (test) | Overall Score48.4 | 13 | |
| Long Video Understanding | LVBench 30-90 min | Accuracy69.2 | 13 | |
| Long Video Understanding | LVBench 4101s | Accuracy58 | 12 | |
| Long-Video Understanding | LVBench 30m~2h | Score56.6 | 12 | |
| Long-form Video Understanding | LVBench w/o sub (test) | Accuracy74.2 | 11 | |
| Long-form video understanding and instruction following | LVBench (test) | Accuracy78.4 | 11 | |
| Video Question Answering | LVBench 2024 (test) | Accuracy66.7 | 8 | |
| Extreme Long Video Comprehension | LVBench | Accuracy51.4 | 8 | |
| Long-form Video Understanding | LVBench w/ sub (test) | Accuracy76.7 | 3 |