Math Reasoning on MMMU-Pro
44.72Accuracy@1Ctrl-R
Evaluation Results
| Method | Links | |
|---|---|---|
| Ctrl-RPower scaling factor (β)=0.22026.03 | 44.72 | |
| Trajectory-Hint2026.03 | 44.34 | |
| Auxiliary Reward2026.03 | 44.18 | |
| OpenVLThinker2026.03 | 43.06 | |
| GRPO2026.03 | 42.66 |
| Method | Links | |
|---|---|---|
| Ctrl-RPower scaling factor (β)=0.22026.03 | 44.72 | |
| Trajectory-Hint2026.03 | 44.34 | |
| Auxiliary Reward2026.03 | 44.18 | |
| OpenVLThinker2026.03 | 43.06 | |
| GRPO2026.03 | 42.66 |