| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Mathematical Reasoning | Beyond-AIME | Avg@5 Score77.6 | 48 | |
| Mathematical Reasoning | Beyond-AIME v1 (test) | Avg@576.6 | 32 | |
| Mathematical Reasoning | Beyond AIME | Accuracy58.8 | 32 | |
| Mathematical Reasoning | Beyond AIME | Pass@122 | 21 | |
| Mathematical Reasoning | Beyond-AIME | Seed Score76.6 | 16 | |
| Mathematical Reasoning | Beyond-AIME | Pass@138.9 | 10 | |
| Mathematical Reasoning | Beyond-AIME VeRA-H VeRA-H Pro | Avg@5 Accuracy (Seeds)58.34 | 1 | |
| Mathematical Reasoning | Beyond-AIME VeRA-E | Avg@5 Accuracy (Seeds)58.34 | 1 |