Multidisciplinary Reasoning on WeMath
61.6AccuracyiVGR-Qwen3-VL-32B
Evaluation Results
| Method | Links | |
|---|---|---|
| iVGR-Qwen3-VL-32BBackbone=Qwen3-VL, Model Size=32B, Training Method=iVGR2026.05 | 61.6 | |
| Qwen3-VL-32BBackbone=Qwen3-VL, Model Size=32B, Training Method=Baseline2026.05 | 60 | |
| iVGR-Qwen3-VL-8BBackbone=Qwen3-VL, Model Size=8B, Training Method=iVGR2026.05 | 55.1 | |
| Qwen3-VL-8BBackbone=Qwen3-VL, Model Size=8B, Training Method=Baseline2026.05 | 49.7 | |
| iVGR-Qwen2.5-VL-7BBackbone=Qwen2.5-VL, Model Size=7B, Training Method=iVGR2026.05 | 41.1 | |
| Qwen2.5-VL-7BBackbone=Qwen2.5-VL, Model Size=7B, Training Method=Baseline2026.05 | 35.3 |