| natural-language-visual-grounding-on-screenspot | Vero-Qwen3I-8B | #1 | Accuracy (%): 93.6 |
| visual-question-answering-vqa-on-countbenchqa | Vero-Qwen3.5-9B | #1 | Accuracy: 95.5 |
| chart-question-answering-on-chartqa | Vero-Qwen3I-8B | #4 | 1:1 Accuracy: 91.6 |
| visual-question-answering-on-v-bench | Vero-Qwen3I-8B | #4 | Accuracy: 89.5 |
| visual-question-answering-vqa-on-blink | Vero-Qwen3.5-9B | #5 | Accuracy: 70.9 |
| computer-use-agents-on-screenspot-pro | Vero-Qwen3I-8B | #16 | Accuracy: 61.4 |
| multimodal-reasoning-on-mathvision | Vero-Qwen3T-8B | #23 | Accuracy: 63.5 |
| visual-question-answering-vqa-on-realworldqa | Vero-Qwen3I-8B | #33 | Accuracy: 73.3 |