| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| ProntoQA | Pass@199.2 | 38 | 1mo ago | ||
| BBH Ded. | Branching | Accuracy92.5 | 28 | 1mo ago | |
| ProofWriter | D&P | End-to-end Accuracy99.67 | 21 | 2mo ago | |
| JustLogic (test) | Complementary Steering | Accuracy59.05 | 18 | 1mo ago | |
| ProofWriter | ADARFT | Pass@197.4 | 18 | 3mo ago | |
| LogicalDeduction | D&P | Accuracy100 | 17 | 2mo ago | |
| ProofWriter | SC+IC (tune) | Calibrated Accuracy92.1 | 8 | 3mo ago |