| CRAD | IQL+SFT+JPOH | Success Rate100 | | 22 | 7d ago |
| SSAD Education | EmoMAS-LLM | Success Rate80 | | 14 | 1mo ago |
| DESRD Emergency | | Success Rate65 | | 14 | 1mo ago |
| SSD Medical | | Success Rate86 | | 14 | 1mo ago |
| CRAD Debt | EmoMAS-LLM | Success Rate100 | | 14 | 1mo ago |
| Student (held-out test) | Vanilla (LLM) | Success Rate100 | | 7 | 7d ago |
| Hospital (test) | Vanilla (LLM) | Success Rate100 | | 7 | 7d ago |
| Disaster (test) | Vanilla (LLM) | Success Rate100 | | 7 | 7d ago |
| CRAD (test) | IQL+SFT | Success Rate100 | | 7 | 7d ago |
| AmazonHistoryPrice evaluated against gpt-5.4-high-reasoning seller (test) | Qwen3-30B-A3B-Instruct-2507-trained | Reward0.408 | | 7 | 1mo ago |
| Student | Vanilla (LLM) | Success Rate100 | | 6 | 7d ago |
| Hospital | Vanilla (LLM) | Success Rate100 | | 6 | 7d ago |
| Disaster | Vanilla (LLM) | Success Rate100 | | 6 | 7d ago |
| Synth | | IR100 | | 5 | 1d ago |
| DND | | IR1 | | 5 | 1d ago |
| GFT scenarios Seller | o3 | Score73.6 | | 5 | 1mo ago |
| CaSiNo | | IR1 | | 3 | 1d ago |
| Negotiation v1 (test) | SEPO | Pay2.17 | | 3 | 2d ago |
| GTBench Negotiation v2 (test) | SEPO | Payoff10.93 | | 3 | 2d ago |
| Craigslist Bargain single-turn | Steered (STAR) | Agreement Rate4.2 | | 3 | 3mo ago |
| DND (test) | CGD | IR0.997 | | 1 | 1d ago |
| CaSiNo (test) | CGD | IR1 | | 1 | 1d ago |
| Synthetic (test) | CGD | IR1 | | 1 | 1d ago |