| temporal-relation-extraction-on-vinoground | VideoLLaMA2-72B | #6 | Text Score: 36.2Video Score: 21.8Group Score: 8.4 |
| video-question-answering-on-mvbench | VideoLLaMA2 (72B) | #6 | Avg.: 62.0 |
| video-question-answering-on-next-qa | VideoLLaMA2.1(7B) | #22 | Accuracy: 75.6 |
| video-question-answering-on-perception-test | VideoLLaMA2 (72B) | #4 | Accuracy (Top-1): 57.5 |
| video-question-answering-on-tvbench | VideoLLaMA2 72B | #10 | Average Accuracy: 48.4 |
| video-question-answering-on-tvbench | VideoLLaMA2 7B | #14 | Average Accuracy: 42.9 |
| video-question-answering-on-tvbench | VideoLLaMA2.1 | #17 | Average Accuracy: 42.1 |
| zero-shot-video-question-answer-on-egoschema-1 | VideoLLaMA2 (72B) | #6 | Accuracy: 63.9 |
| zero-shot-video-question-answer-on-video-mme | VideoLLaMA2 (72B) | #5 | Accuracy (%): 60.9 |
| zero-shot-video-question-answer-on-video-mme-1 | VideoLLaMA2 (72B) | #7 | Accuracy (%): 63.1 |
| zero-shot-video-question-answer-on-vnbench | VideoLLaMA2 | #8 | Accuracy: 4.5 |