Multidisciplinary Reasoning on MMStar (Accuracy)
75.1AccuracyiVGR-Qwen3-VL-32B
Evaluation Results
| Method | Links | |
|---|---|---|
| iVGR-Qwen3-VL-32BBackbone=Qwen3-VL, Model Size=32B, Training Method=iVGR2026.05 | 75.1 | |
| Qwen3-VL-32BBackbone=Qwen3-VL, Model Size=32B, Training Method=Baseline2026.05 | 72.3 | |
| iVGR-Qwen3-VL-8BBackbone=Qwen3-VL, Model Size=8B, Training Method=iVGR2026.05 | 69.7 | |
| Qwen3-VL-8BBackbone=Qwen3-VL, Model Size=8B, Training Method=Baseline2026.05 | 67.9 | |
| iVGR-Qwen2.5-VL-7BBackbone=Qwen2.5-VL, Model Size=7B, Training Method=iVGR2026.05 | 66.3 | |
| Qwen2.5-VL-7BBackbone=Qwen2.5-VL, Model Size=7B, Training Method=Baseline2026.05 | 63.9 |