| Benchmark | Model | Rank | Results |
|---|---|---|---|
| video-question-answering-on-situated | All-in-one | #10 | Average Accuracy: 47.5 |
| video-retrieval-on-msr-vtt-1ka | All-in-one-B | #35 | text-to-video R@1: 37.9text-to-video R@5: 68.1… |
| visual-question-answering-on-msrvtt-qa-1 | All-in-one-B | #12 | Accuracy: 0.443 |
| visual-question-answering-on-msvd-qa-1 | All-in-one-B | #18 | Accuracy: 0.483 |