| Benchmark | Model | Rank | Results |
|---|---|---|---|
| visual-question-answering-vqa-on-seed-seedbench | LLaDA-V | #2 | Accuracy: 82.9 |
| visual-question-answering-vqa-on-mme | LLaDA-V | #16 | Score: 1998 |
| video-question-answering-on-mlvu | LLaDA-V | #53 | Accuracy: 59.5 |
| visual-question-answering-vqa-on-realworldqa | LLaDA-V | #77 | Accuracy: 63.2 |
| vision-language-understanding-on-mmstar | LLaDA-V | #83 | Accuracy: 60.1 |
| multimodal-reasoning-on-mmmu | LLaDA-V | #101 | Accuracy: 48.6 |