| text-to-video-generation-on-vbench | PixelUMM 8B MoT | #25 | VBench Total Score: 83.24VBench Quality Score: 84.1 |
| video-question-answering-on-mvbench | PixelUMM 8B MoT | #27 | Avg.: 70.53 |
| visual-question-answering-vqa-on-blink | PixelUMM 8B MoT | #41 | Accuracy: 53.46 |
| zero-shot-video-question-answer-on-video-mme-w-o-subs | PixelUMM 8B MoT | #49 | Accuracy (%): 57.33 |
| video-question-answering-on-lvbench | PixelUMM 8B MoT | #50 | Accuracy: 40.41 |
| chart-question-answering-on-chartqa | PixelUMM 8B MoT | #56 | 1:1 Accuracy: 82.96 |
| multimodal-reasoning-on-mmmu-pro | PixelUMM 8B MoT | #60 | Accuracy: 27.63 |
| vision-language-understanding-on-mmstar | PixelUMM 8B MoT | #91 | Accuracy: 53.99 |
| text-to-image-generation-on-geneval | PixelUMM 8B MoT | #118 | Overall: 0.77 |
| multimodal-reasoning-on-mmmu | PixelUMM 8B MoT | #121 | Accuracy: 41.67 |