Role-playing on RoleBench Chinese (instruction generalization)
36.4Win Rate (vs GPT-4)
RoleGLM
Updated 4d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2023.10 | 36.4 | 52.4 | |
2023.10 | 28.9 | 19.9 | |
2023.10 | 28.2 | 19 | |
2023.10 | 24.2 | 19.6 |
RoleGLM
| Method | Links | ||
|---|---|---|---|
2023.10 | 36.4 | 52.4 | |
2023.10 | 28.9 | 19.9 | |
2023.10 | 28.2 | 19 | |
2023.10 | 24.2 | 19.6 |