Visual Perception and Counting on BLINK
62.6Accuracy (BLINK)MiMo-VL-7B +PC
Evaluation Results
| Method | Links | |
|---|---|---|
| MiMo-VL-7B +PCBackbone Model=MiMo-VL-7B, Training Paradigm (+PC)=Yes2026.03 | 62.6 | |
| MiMo-VL-7BBackbone Model=MiMo-VL-7B, Training Paradigm (+PC)=No2026.03 | 62.5 | |
| Qwen2.5-VL-7B +PCBackbone Model=Qwen2.5-VL-7B, Training Paradigm (+PC)=Yes2026.03 | 56.6 | |
| Qwen2.5-VL-7BBackbone Model=Qwen2.5-VL-7B, Training Paradigm (+PC)=No2026.03 | 56.4 | |
| Qwen2.5-VL-3B +PCBackbone Model=Qwen2.5-VL-3B, Training Paradigm (+PC)=Yes2026.03 | 48.9 | |
| Qwen2.5-VL-3BBackbone Model=Qwen2.5-VL-3B, Training Paradigm (+PC)=No2026.03 | 47.6 |