| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Math Reasoning | MathBench EN | Score50.6 | 14 | |
| Math Reasoning | MathBench-CN | General Score48 | 14 | |
| Bilingual Mathematical Reasoning | MathBench EN | Accuracy40.1 | 13 | |
| Bilingual Mathematical Reasoning | MathBench CN | Accuracy46.2 | 13 | |
| Mathematical Reasoning | MathBench College | Accuracy78 | 3 | |
| Mathematical Reasoning | MathBench High | Accuracy84 | 3 | |
| Mathematical Reasoning | MathBench Middle | Accuracy84.67 | 3 | |
| Mathematical Reasoning | MathBench Arithmetic | Accuracy75 | 3 |