| zero-shot-video-question-answer-on-longvideobench | Molmo2-4B | #1 | Accuracy (% ): 68.0 |
| video-question-answering-on-perception-test-test | Molmo2-8B | #2 | Accuracy: 82.1 |
| video-question-answering-on-tomato | Molmo2-4B | #2 | Accuracy: 39.8 |
| visual-question-answering-vqa-on-textvqa-val | Molmo2-8B | #3 | Accuracy: 85.7 |
| video-question-answering-on-tempcompass-mcq | Molmo2-8B | #5 | Accuracy: 73.4 |
| video-question-answering-on-mvbench | Molmo2-8B | #7 | Avg.: 75.9 |
| visual-question-answering-vqa-on-infographicvqa | Molmo2-8B | #8 | ANLS: 80.1 |
| object-counting-on-countbench | Molmo2-O-7B | #9 | Accuracy: 95.1 |
| visual-question-answering-vqa-on-realworldqa | Molmo2-8B | #18 | Accuracy: 77.6 |
| zero-shot-video-question-answer-on-egoschema-fullset | Molmo2-8B | #22 | Accuracy: 62.0 |
| visual-question-answering-on-docvqa-test | Molmo2-8B | #23 | ANLS: 0.932 |
| video-question-answering-on-lvbench | Molmo2-4B | #26 | Accuracy: 53.9 |
| zero-shot-video-question-answer-on-video-mme-w-o-subs | Molmo2-8B | #27 | Accuracy (%): 69.9 |
| visual-question-answering-vqa-on-blink | Molmo2-4B | #29 | Accuracy: 57.5 |
| chart-question-answering-on-chartqa | Molmo2-4B | #38 | 1:1 Accuracy: 86.1 |
| multimodal-reasoning-on-mmmu | Molmo2-8B | #86 | Accuracy: 53.0 |
| multimodal-reasoning-on-mathvista | Molmo2-8B | #95 | Accuracy: 58.9 |