Scientific Reasoning on MMK12 Chem
63.7AccuracyV-STAR
Evaluation Results
| Method | Links | |
|---|---|---|
| V-STARData Size=40k2026.04 | 63.7 | |
| OpenVLThinkerData Size=59.2k2026.04 | 60.6 | |
| ThinkLite-VLData Size=11k2026.04 | 57.9 | |
| VL-CogitoData Size=80k2026.04 | 57.5 | |
| VL-RethinkerData Size=39k2026.04 | 57.4 | |
| Qwen2.5VL2026.04 | 56.4 | |
| Vision-R1Data Size=210k2026.04 | 55.4 | |
| R1-OnevisionData Size=155k2026.04 | 39.8 |