Social Simulation on Sotopia standard (test)
8.92Goal Score
The Stackelberg Speaker + MetaMind
Updated 4d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| 8.92 | 4.2 | ||
2025.10 | 8.7 | 4.03 | |
| 8.58 | 3.95 | ||
2025.10 | 8.45 | 3.88 | |
2025.10 | 8.43 | 3.85 | |
2025.10 | 8.13 | 3.63 | |
2025.10 | 8.07 | 3.67 | |
2025.10 | 7.62 | 3.44 |