| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Mixed regime | Accuracy72.4 | 15 | 1mo ago | ||
| Social regime | Situational leadership controller | Accuracy51.3 | 15 | 1mo ago | |
| Closed regime | MAD | Accuracy87.7 | 15 | 1mo ago | |
| AlphaNLI | Accuracy93.7 | 15 | 1mo ago | ||
| MMLU-Pro Debate | Concise | Success Rate (SR)65.7 | 10 | 3mo ago |