| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| SingleOp Near-shift OOD | TV Score | Accuracy95.75 | 3 | 4d ago | |
| SingleEq Near-shift OOD | TV Score | Accuracy93.15 | 3 | 4d ago | |
| AddSub Near-shift OOD | Input Embedding | Accuracy79.16 | 3 | 4d ago | |
| SVAMP Near-shift OOD | TV Score | Accuracy94.88 | 3 | 4d ago | |
| GSM8K Near-shift OOD | TV Score | Accuracy93.39 | 3 | 4d ago | |
| Precalculus Far-shift OOD | TV Score | Accuracy99.28 | 3 | 4d ago | |
| Num. Theory (Far-shift OOD) | TV Score | Accuracy92.08 | 3 | 4d ago | |
| Cnt.&Prob (Far-shift OOD) | TV Score | Accuracy93.74 | 3 | 4d ago | |
| Geometry Far-shift OOD | TV Score | Accuracy0.9447 | 3 | 4d ago | |
| Algebra Far-shift OOD | TV Score | Accuracy93.88 | 3 | 4d ago |