| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Mathematical Reasoning | AQUA-RAT | Accuracy69.7 | 57 | |
| Algebraic Question Answering | AQUA-RAT Synthetic NIID 1.0 (test) | Accuracy28 | 7 | |
| Algebraic Question Answering | AQUA-RAT Synthetic IID 1.0 (test) | Accuracy29.9 | 7 | |
| Mathematical Reasoning | AQUA-RAT STREET | Answer Accuracy78 | 3 | |
| Mathematical Reasoning | AQUA-RAT standard (test) | ACC (%)40.16 | 3 |