Reward alignment on RBM-EVAL ID
0.94Pearson r (VOC)ACE-Brain-0.5
Evaluation results
| Method | Links | |
|---|---|---|
| ACE-Brain-0.52026.07 | 0.94 | |
| ROBOMETERTraining Data=RBM-1M data2026.03 | 0.92 | |
| Robometer-4B2026.07 | 0.92 | |
| ROBOMETERTraining Data=RoboReward Training Data2026.03 | 0.84 | |
| RoboReward-8BTraining Data=RoboReward Training Data2026.03 | 0.82 | |
| RoboReward-8B2026.07 | 0.82 | |
| RoboDopamine-8B2026.07 | 0.79 | |
| RoboReward-4BTraining Data=RoboReward Training Data2026.03 | 0.77 | |
| Qwen3-VL-8B2026.07 | 0.73 | |
| ReWiNDTraining Data=RBM-1M data2026.03 | 0.46 | |
| GVLTraining Data=Baselines2026.03 | 0.16 | |
| VLACTraining Data=Baselines2026.03 | 0.16 | |
| VLAC-8B2026.07 | 0.16 | |
| RoboDopamineTraining Data=Baselines2026.03 | 0.13 |