| visual-question-answering-vqa-on-vibe-eval | LLaVA-OneVision-72B | #1 | Accuracy: 50.7 |
| temporal-relation-extraction-on-vinoground | LLaVA-OneVision-Qwen2-72B | #2 | Text Score: 48.4Video Score: 35.2Group Score: 21.8 |
| temporal-relation-extraction-on-vinoground | LLaVA-OneVision-Qwen2-7B | #3 | Text Score: 41.6Video Score: 29.4Group Score: 14.6 |
| video-question-answering-on-implicitqa | LLaVA-OneVision - 7B | #3 | Average Accuracy: 43.4Macro Average Accuracy: 46.4 |
| zero-shot-video-question-answer-on-vnbench | LLaVA-OneVision-72B | #3 | Accuracy: 58.7 |
| zero-shot-video-question-answer-on-vnbench | LLaVA-OneVision-7B | #4 | Accuracy: 51.8 |
| visual-question-answering-vqa-on-seed-seedbench | LLaVA-OneVision-72B | #5 | Accuracy: 78.0 |
| video-question-answering-on-ovbench | LLaVA-OneVision (7B) | #6 | AVG: 49.5 |
| visual-question-answering-vqa-on-vlm2-bench | LLaVA-OneVision-7B | #6 | GC-mat: 16.60GC-trk: 13.70OC-cpr: 47.22OC-cnt: 56.17… |
| zero-shot-video-question-answer-on-longvideobench | LLaVA-OneVision-72B | #6 | Accuracy (% ): 61.3 |
| visual-question-answering-vqa-on-infographicvqa | LLaVA-OneVision-72B | #10 | ANLS: 74.9 |
| visual-question-answering-vqa-on-mme | LLaVA-OneVision-72B | #11 | Score: 2261 |
| video-question-answering-on-next-qa | LLaVA-OV(72B) | #12 | Accuracy: 80.2 |
| video-question-answering-on-next-qa | LLaVA-OV(7B) | #14 | Accuracy: 79.4 |
| 3d-question-answering-3d-qa-on-scanqa-test-w-objects | LLaVA-NeXT-Video | #15 | Exact Match: 18.7BLEU-4: 9.8ROUGE: 27.8METEOR: 9.1CIDEr: 46.2 |
| visual-question-answering-on-v-bench | LLaVA-OneVision7B | #19 | Accuracy: 74.46 |
| 3d-question-answering-3d-qa-on-sqa3d | LLaVA-NeXT-Video | #20 | Exact Match: 34.2 |
| zero-shot-video-question-answer-on-egoschema-fullset | LLaVA-OneVision-72B | #22 | Accuracy: 62.0 |
| video-question-answering-on-video-mme-with-subtitles | LLaVA-OneVision-72B (w/ subtitles) | #27 | Accuracy: 69.5 |
| visual-question-answering-on-mm-vet | LLaVA-OneVision-72B | #30 | GPT-4 score: 63.7 |
| visual-question-answering-on-mm-vet | LLaVA-OneVision-7B | #51 | GPT-4 score: 57.5 |
| visual-question-answering-on-mm-vet | LLaVA-OneVision-0.5B | #184 | GPT-4 score: 29.1 |
| visual-question-answering-on-docvqa-test | LLaVA-OneVision-72B | #36 | ANLS: 0.913 |
| visual-question-answering-vqa-on-blink | LLaVA-OneVision-72B | #37 | Accuracy: 55.4 |
| zero-shot-video-question-answer-on-video-mme-w-o-subs | LLaVA-OneVision-72B | #38 | Accuracy (%): 66.2 |
| visual-question-answering-vqa-on-realworldqa | LLaVA-OneVision-72B | #41 | Accuracy: 71.9 |
| video-question-answering-on-mlvu | LLaVA-OneVision-72B | #44 | Accuracy: 68.0 |
| chart-question-answering-on-chartqa | LLaVA-OneVision-72B | #53 | 1:1 Accuracy: 83.7 |
| vision-language-understanding-on-mmstar | LLaVA-OneVision-72B | #59 | Accuracy: 66.1 |
| multimodal-reasoning-on-mmmu | LLaVA-OneVision-72B | #69 | Accuracy: 56.8 |
| video-question-answering-on-mvbench | LLaVA-OneVision-72B | #71 | Avg.: 59.4 |
| multimodal-reasoning-on-mathvista | LLaVA-OneVision-72B | #76 | Accuracy: 67.5 |