Critic Accuracy on LBM dataset
98BimanBike AccuracyRobot Critics
Evaluation results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Robot Critics2026.06 | 98 | 98.8 | 88.9 | 100 | 91.9 | 88.5 | 77.8 | 76.3 | 90 | |
| ROVER2026.06 | 71.7 | 54.5 | 75.8 | 61.5 | 64.6 | 71.2 | 49 | 54.7 | 62.9 | |
| Gemini 32026.06 | 47.3 | 49.2 | 54.5 | 51 | 69.7 | 60.8 | 51 | 59.6 | 55.4 | |
| ProgressLM2026.06 | 44.3 | 70.9 | 61.3 | 61.5 | 66.1 | 66.7 | 61.5 | 60 | 61.5 |