| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Arithmetic Reasoning | AddSub | Accuracy98.2 | 76 | |
| Mathematical Reasoning | ADDSUB | Solve Rate93.1 | 22 | |
| Arithmetic Reasoning | AddSub (test) | Accuracy96.71 | 8 | |
| Online Out-of-Distribution Detection | AddSub Near-shift OOD | Accuracy79.16 | 3 |