| visual-question-answering-vqa-on-blink | MOSS-VL-Instruct-0708 | #2 | Accuracy: 78.0 |
| video-question-answering-on-tomato | MOSS-VL-Instruct-0708 | #3 | Accuracy: 39.5 |
| object-hallucination-evaluation-on-pope | MOSS-VL-Instruct-0708 | #4 | F1: 89.4 |
| object-counting-on-countbench | MOSS-VL-Instruct-0708 | #22 | Accuracy: 85.9 |
| zero-shot-video-question-answer-on-video-mme-w-o-subs | MOSS-VL-Instruct-0708 | #28 | Accuracy (%): 68.1 |
| video-question-answering-on-lvbench | MOSS-VL-Instruct-0708 | #33 | Accuracy: 51.1 |
| video-question-answering-on-mvbench | MOSS-VL-Instruct-0708 | #45 | Avg.: 66.7 |
| vision-language-understanding-on-mmstar | MOSS-VL-Instruct-0708 | #57 | Accuracy: 66.0 |
| visual-question-answering-vqa-on-realworldqa | MOSS-VL-Instruct-0708 | #59 | Accuracy: 68.0 |