Social Simulation on Sotopia hard (test)
7.59Goal ScoreThe Stackelberg Speaker + MetaMind
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| The Stackelberg Speaker + MetaMindBase Agent=MetaMind2025.10 | 7.59 | 3.85 | |
| MetaMind2025.10 | 7.16 | 3.6 | |
| The Stackelberg Speaker + ReActBase Agent=ReAct2025.10 | 7.12 | 3.55 | |
| ReCon2025.10 | 7.08 | 3.48 | |
| ReAct2025.10 | 7.06 | 3.45 | |
| SDPO2025.10 | 6.35 | 3.14 | |
| SOTOPIA-Ω2025.10 | 6.31 | 3.03 | |
| SOTOPIA-π2025.10 | 5.34 | 2.76 |