| computer-use-agents-on-osworld-verified-369-tasks-50-steps | EvoCUA-32B | #1 | Success Rate: 56.7 |
| computer-use-agents-on-osw-g-osworld-g | EvoCUA-OpenCUA-72B | #6 | Accuracy: 67.65 |
| computer-use-agents-on-screenspot-pro | EvoCUA-OpenCUA-72B | #10 | Accuracy: 63.24 |
| computer-use-agents-on-screenspot-v2 | EvoCUA-OpenCUA-72B | #17 | Accuracy: 93.47 |
| multimodal-reasoning-on-mathvista | EvoCUA-32B | #28 | Accuracy: 80.40 |
| vision-language-understanding-on-mmstar | EvoCUA-32B | #28 | Accuracy: 73.20 |
| multimodal-reasoning-on-mmmu-pro | EvoCUA-32B | #31 | Accuracy: 59.16 |
| optical-character-recognition-ocr-on-ocrbench | EvoCUA-32B | #36 | Score: 853.5 |
| multimodal-reasoning-on-mmmu | EvoCUA-32B | #39 | Accuracy: 68.11 |