| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Mathematical Reasoning | MMATH | Accuracy78.4 | 36 | |
| Multilingual Mathematical Reasoning | MMATH All Languages (test) | Average Score (All)28.6 | 22 | |
| Multilingual Mathematical Reasoning | MMATH Out-of-Domain Languages (test) | Vietnamese Accuracy30.1 | 22 | |
| Multilingual Mathematical Reasoning | MMATH In-Domain Languages (test) | Accuracy (Ar)26.3 | 22 | |
| Math Problem Solving | MMATH (test) | Accuracy (Ar)27.1 | 20 | |
| Mathematical Reasoning | MMATH (test) | Ar Score37.4 | 10 |