| computer-use-agents-on-mobileworld | LLaDA-UI | #5 | Success Rate: 25.6 |
| infographic-visual-question-answering-on-infovqa | LLaDA-UI (pre-training) | #6 | ANLS: 71.5 |
| visual-question-answering-vqa-on-ai2d-test-with-mask | LLaDA-UI (pre-training) | #7 | Accuracy: 80.2 |
| computer-use-agents-on-webvoyager | LLaDA-UI | #9 | Success Rate: 56.9 |
| visual-question-answering-vqa-on-simplevqa | LLaDA-UI (pre-training) | #11 | Accuracy: 44.3 |
| computer-use-agents-on-osworld-verified | LLaDA-UI | #12 | Success Rate: 29.4 |
| chart-question-answering-on-charxiv-dq | LLaDA-UI (pre-training) | #14 | Accuracy: 72.2 |
| visual-question-answering-vqa-on-mmbench-cn | LLaDA-UI (pre-training) | #15 | Accuracy: 77.7 |
| mathematical-reasoning-on-mathverse | LLaDA-UI (pre-training) | #18 | Accuracy: 48.0 |
| object-counting-on-countbench | LLaDA-UI (pre-training) | #20 | Accuracy: 86.2 |
| visual-question-answering-vqa-on-mmbench-en | LLaDA-UI (pre-training) | #22 | Accuracy: 80.5 |
| computer-use-agents-on-androidworld | LLaDA-UI | #25 | Success Rate: 53.5 |
| chart-question-answering-on-charxiv-rq | LLaDA-UI (pre-training) | #28 | Accuracy: 35.6 |
| computer-use-agents-on-screenspot-pro | LLaDA-UI | #28 | Accuracy: 52.9 |
| computer-use-agents-on-screenspot-v2 | LLaDA-UI | #30 | Accuracy: 90.7 |
| optical-character-recognition-ocr-on-ocrbench | LLaDA-UI (pre-training) | #35 | Score: 855 |
| visual-question-answering-on-docvqa-test | LLaDA-UI (pre-training) | #35 | ANLS: 0.915 |
| chart-question-answering-on-chartqa | LLaDA-UI (pre-training) | #47 | 1:1 Accuracy: 84.8 |
| multimodal-reasoning-on-mathvista | LLaDA-UI (pre-training) | #64 | Accuracy: 70.5 |
| multimodal-reasoning-on-mmmu | LLaDA-UI (pre-training) | #68 | Accuracy: 56.2 |
| visual-question-answering-vqa-on-realworldqa | LLaDA-UI (pre-training) | #76 | Accuracy: 63.5 |
| vision-language-understanding-on-mmstar | LLaDA-UI (pre-training) | #79 | Accuracy: 61.3 |