| zero-shot-video-question-answer-on-vnbench | LLaVA-NeXT-Video-7B | #6 | Accuracy: 20.1 |
| object-hallucination-evaluation-on-pope | LLaVA-NeXT-Interleave 14B | #7 | F1: 87.9 |
| video-question-answering-on-next-qa | LLaVA-NeXT-Interleave(14B) | #15 | Accuracy: 79.1 |
| video-question-answering-on-next-qa | LLaVA-NeXT-Interleave(7B) | #18 | Accuracy: 78.2 |
| video-question-answering-on-next-qa | LLaVA-NeXT-Interleave(DPO) | #19 | Accuracy: 77.9 |
| visual-question-answering-vqa-on-blink | LLaVA-NeXT-Interleave 14B | #42 | Accuracy: 52.1 |
| visual-question-answering-on-docvqa-test | LLaVA-NeXT-Interleave 14B | #73 | ANLS: 0.789 |
| video-question-answering-on-mvbench | LLaVA-NeXT-Interleave 14B | #76 | Avg.: 54.9 |
| chart-question-answering-on-chartqa | LLaVA-NeXT-Interleave 14B | #88 | 1:1 Accuracy: 71.2 |