| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| AmazonHistoryPrice CI 1.0 (test) | Count44 | 28 | 1mo ago | ||
| AmazonHistoryPrice ALL 1.0 (test) | Count930 | 28 | 1mo ago | ||
| AmazonHistoryPrice (held-out test) | Qwen3-30B-A3B-Instruct-2507-trained | Reward0.7664 | 16 | 5d ago | |
| Held-Out (test) | Qwen3-30B-A3B-Instruct-2507-trained | Reward0.7664 | 16 | 5d ago | |
| AmazonHistoryPrice MI 1.0 (test) | Count835 | 14 | 1mo ago | ||
| AmazonHistoryPrice (test) | The Stackelberg Speaker + ReAct | Deal Rate46.8 | 4 | 4d ago | |
| Bargaining Benchmark 20 Products CI | Mistral-7B-Instruct | Deal Rate5,000 | 4 | 1mo ago | |
| Bargaining Benchmark MI 20 Products | Deal Rate52.94 | 4 | 1mo ago | ||
| Bargaining Benchmark 20 Products ALL | Valid Rate0.95 | 4 | 1mo ago |
