| video-based-generative-performance-benchmarking-contextual-understanding-on-videoinstruct | PLLaVA-34B | #2 | gpt-score: 3.9 |
| video-based-generative-performance-benchmarking-correctness-of-information-on-videoinstruct | PLLaVA-34B | #2 | gpt-score: 3.60 |
| video-based-generative-performance-benchmarking-detail-orientation-on-videoinstruct | PLLaVA-34B | #2 | gpt-score: 3.20 |
| zeroshot-video-question-answer-on-activitynet-qa | PLLaVA (34B) | #2 | Accuracy: 60.9Confidence Score: 3.7 |
| zeroshot-video-question-answer-on-msrvtt-qa | PLLaVA (34B) | #2 | Accuracy: 68.7Confidence Score: 3.6 |
| video-based-generative-performance-benchmarking-on-videoinstruct | PLLaVA-34B | #4 | mean: 3.32Correctness of Information: 3.60Detail Orientation: 3.20… |
| zeroshot-video-question-answer-on-tgif-qa | PLLaVA | #4 | Accuracy: 80.6Confidence Score: 4.3 |
| video-based-generative-performance-benchmarking-consistency-on-videoinstruct | PLLaVA-34B | #5 | gpt-score: 3.25 |
| zeroshot-video-question-answer-on-msvd-qa | PLLaVA (34B) | #5 | Accuracy: 79.9Confidence Score: 4.2 |
| video-based-generative-performance-benchmarking-temporal-understanding-on-videoinstruct | PLLaVA-34B | #6 | gpt-score: 2.67 |
| video-question-answering-on-tvbench | PLLaVA-34B | #15 | Average Accuracy: 42.3 |
| video-question-answering-on-tvbench | PLLaVA-13B | #19 | Average Accuracy: 36.4 |
| video-question-answering-on-tvbench | PLLaVA-7B | #22 | Average Accuracy: 34.9 |
| video-question-answering-on-mvbench | PLLaVA | #75 | Avg.: 58.1 |