| video-question-answering-on-next-qa | VideoLLaMA3(7B) | #3 | Accuracy: 84.5 |
| video-question-answering-on-perception-test-test | VideoLLaMA3 7B | #3 | Accuracy: 72.8 |
| visual-question-answering-vqa-on-infographicvqa | VideoLLaMA3 7B | #9 | ANLS: 78.9 |
| visual-question-answering-vqa-on-mme | VideoLLaMA3 7B | #11 | Score: 2102 |
| visual-question-answering-vqa-on-mme | VideoLLaMA3 2B | #18 | Score: 1901 |
| visual-question-answering-on-docvqa-test | VideoLLaMA3 7B | #12 | ANLS: 0.949 |
| visual-question-answering-on-docvqa-test | VideoLLaMA3 2B | #30 | ANLS: 0.919 |
| video-question-answering-on-tempcompass-overall | VideoLLaMA3 7B | #13 | Accuracy: 68.1 |
| zero-shot-video-question-answer-on-egoschema-fullset | VideoLLaMA3 7B | #19 | Accuracy: 63.3 |
| video-question-answering-on-video-mme-with-subtitles | VideoLLaMA3 7B (w/ subs) | #25 | Accuracy: 70.3 |
| video-question-answering-on-mlvu | VideoLLaMA3 7B | #28 | Accuracy: 73.0 |
| video-question-answering-on-mmvu | VideoLLaMA3 7B | #31 | Accuracy: 44.1 |
| video-question-answering-on-mvbench | VideoLLaMA3 7B | #31 | Avg.: 69.7 |
| chart-question-answering-on-chartqa | VideoLLaMA3 7B | #33 | 1:1 Accuracy: 86.3 |
| chart-question-answering-on-chartqa | VideoLLaMA3 2B | #69 | 1:1 Accuracy: 79.8 |
| zero-shot-video-question-answer-on-video-mme-w-o-subs | VideoLLaMA3 7B | #36 | Accuracy (%): 66.2 |
| visual-question-answering-vqa-on-realworldqa | VideoLLaMA3 7B | #37 | Accuracy: 72.7 |
| visual-question-answering-vqa-on-realworldqa | VideoLLaMA3 2B | #65 | Accuracy: 67.3 |
| video-question-answering-on-lvbench | VideoLLaMA3 7B | #43 | Accuracy: 45.3 |
| optical-character-recognition-ocr-on-ocrbench | VideoLLaMA3 7B | #44 | Score: 828 |
| visual-question-answering-vqa-on-blink | VideoLLaMA3 2B | #47 | Accuracy: 44.2 |
| multimodal-reasoning-on-mathvision | VideoLLaMA3 7B | #54 | Accuracy: 26.2 |
| multimodal-reasoning-on-mathvision | VideoLLaMA3 2B | #62 | Accuracy: 15.5 |
| multimodal-reasoning-on-mmmu-pro | VideoLLaMA3 7B | #58 | Accuracy: 33.6 |
| multimodal-reasoning-on-mmmu-pro | VideoLLaMA3 2B | #59 | Accuracy: 28.6 |
| multimodal-reasoning-on-mathvista | VideoLLaMA3 7B | #75 | Accuracy: 67.1 |
| multimodal-reasoning-on-mathvista | VideoLLaMA3 2B | #93 | Accuracy: 59.2 |
| multimodal-reasoning-on-mmmu | VideoLLaMA3 7B | #100 | Accuracy: 48.8 |
| multimodal-reasoning-on-mmmu | VideoLLaMA3 2B | #111 | Accuracy: 45.3 |