| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| SOTOPIA-Hard GPT-4o-as-Partner | AMPO | Goal Score7.68 | 24 | 1mo ago | |
| SOTOPIA GPT-4o-as-Partner | AMPO | Goal Score8.75 | 24 | 1mo ago | |
| SOTOPIA-Hard (Self-Play) | AMPO | GOAL Score8.06 | 24 | 1mo ago | |
| SOTOPIA (Self-Play) | AMPO | Goal Score9.08 | 24 | 1mo ago |