Social Interaction Evaluation on SOTOPIA-Hard (Self-Play)
8.06GOAL Score
AMPO
Updated 3mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2025.05 | 8.06 | 3.68 | |
2025.05 | 7.85 | 3.54 | |
2025.05 | 7.59 | 3.44 | |
2025.05 | 7.44 | 3.41 | |
2025.05 | 7.31 | 3.51 | |
2025.05 | 7.21 | 3.5 | |
2025.05 | 7.14 | 3.47 | |
2025.05 | 6.97 | 3.46 | |
2025.05 | 6.93 | 3.31 | |
2025.05 | 6.82 | 3.12 | |
2025.05 | 6.79 | 3.27 | |
2025.05 | 6.63 | 3.31 | |
2025.05 | 6.39 | 3.1 | |
2025.05 | 6.34 | 3.09 | |
2025.05 | 6.33 | 3.09 | |
2025.05 | 6.21 | 3.01 | |
2025.05 | 5.89 | 2.85 | |
2025.05 | 5.86 | 2.73 | |
2025.05 | 5.69 | 2.71 | |
2025.05 | 5.67 | 2.55 | |
2025.05 | 5.35 | 2.41 | |
| 5.34 | 2.57 | ||
2025.05 | 5.14 | 2.36 | |
2025.05 | 5.11 | 2.36 |