| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Math problem solving | Math Domain (AIME24, Math-OAI, Minerva, Olympiad, ACM23) Qwen2.5-7B (10% selection) | AIME24 Score7.71 | 18 | |
| Mathematical Problem Solving | Math Domain (Out-of-Domain: MATH500, AIME24, Minerva-Math, AMC23) | MATH500 Score91.8 | 11 | |
| Mathematical Reasoning | Math Domain In-Domain | MATH50091 | 11 | |
| Mathematical Reasoning | Math Domain | Avg Accuracy66.45 | 7 |