Social Skill Simulation on Sotopia Hard
49.2Primary Metric
OSIM 8B
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.06 | 49.2 | |
2026.06 | 45.6 | |
2026.06 | 32.4 | |
2026.06 | 31.9 | |
2026.06 | 31.7 | |
2026.06 | 28.3 | |
2026.06 | 27.8 | |
2026.06 | 27.7 | |
2026.06 | 21.4 |
OSIM 8B
| Method | Links | |
|---|---|---|
2026.06 | 49.2 | |
2026.06 | 45.6 | |
2026.06 | 32.4 | |
2026.06 | 31.9 | |
2026.06 | 31.7 | |
2026.06 | 28.3 | |
2026.06 | 27.8 | |
2026.06 | 27.7 | |
2026.06 | 21.4 |