| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Math Tutoring | BigMath In-Domain | Rsol57.4 | 21 | |
| Math Reasoning | BigMath level 5 | Average Accuracy43.1 | 18 | |
| Math Reasoning | BigMath level 4 | Accuracy66.3 | 18 | |
| Mathematical Reasoning | BigMath (test) | True Accuracy48.4 | 6 | |
| Mathematical Reasoning | Bigmath Mathematics | Score47.33 | 3 |