| visual-question-answering-vqa-on-mmvp | MiMo-VL-7B-SFT + VisionFoundry-10K | #1 | Paired Accuracy: 57.3 |
| vision-language-understanding-on-mmbench-v1-1 | MiMo-VL-7B-SFT + VisionFoundry-10K | #19 | Accuracy: 81.6 |
| visual-question-answering-vqa-on-blink | MiMo-VL-7B-SFT + VisionFoundry-10K | #28 | Accuracy: 58.7 |
| computer-use-agents-on-screenspot-pro | Qwen2.5-VL-3B-Instruct + VisionFoundry-10K | #49 | Accuracy: 20.2 |
| visual-question-answering-vqa-on-realworldqa | MiMo-VL-7B-SFT + VisionFoundry-10K | #63 | Accuracy: 67.5 |
| vision-language-understanding-on-mmstar | MiMo-VL-7B-SFT + VisionFoundry-10K | #74 | Accuracy: 62.7 |
| multimodal-reasoning-on-mathvista | Qwen2.5-VL-3B-Instruct + VisionFoundry-10K | #88 | Accuracy: 62.9 |
| multimodal-reasoning-on-mmmu | MiMo-VL-7B-SFT + VisionFoundry-10K | #88 | Accuracy: 52.3 |