| visual-question-answering-on-gqa-test-dev | Video-LLaVA-7B | #6 | Accuracy: 60.3 |
| zeroshot-video-question-answer-on-tgif-qa | Video-LLaVA-7B | #10 | Accuracy: 70.0Confidence Score: 4.0 |
| temporal-relation-extraction-on-vinoground | Video-LLaVA-7B | #11 | Text Score: 24.8Video Score: 25.8Group Score: 6.6 |
| video-question-answering-on-activitynet-qa | Video-LLaVA | #12 | Accuracy: 45.3Confidence score: 3.3 |
| zeroshot-video-question-answer-on-msrvtt-qa | Video-LLaVA-7B | #17 | Accuracy: 59.2Confidence Score: 3.5 |
| zeroshot-video-question-answer-on-msvd-qa | Video-LLaVA-7B | #18 | Accuracy: 70.7Confidence Score: 3.9 |
| zeroshot-video-question-answer-on-activitynet-qa | Video-LLaVA | #23 | Accuracy: 45.3Confidence Score: 3.3 |
| visual-question-answering-vqa-on-textvqa-val | Video-LLaVA-7B | #24 | Accuracy: 51.8 |
| object-hallucination-evaluation-on-pope | Video-LLaVA-7B | #29 | F1: 83.3 |
| visual-question-answering-vqa-on-mmbench-en | Video-LLaVA-7B | #36 | Accuracy: 60.9 |
| visual-question-answering-on-mm-vet | Video-LLaVA | #164 | GPT-4 score: 32.0 |