Mathematical Reasoning on AIME AM24 AM25 (2024 2025)
80.63AIME 2024 ScoreT3S
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| T3STeacher=DeepSeek-R1, Training Dataset=BOBA-2002026.01 | 80.63 | 73.96 | 77.3 | |
| T3STeacher=DeepSeek-R1, Training Dataset=S1K-2002026.01 | 80 | 73.13 | 76.57 | |
| T3STeacher=QWQ, Training Dataset=BOBA-2002026.01 | 77.5 | 70.83 | 74.17 | |
| RRTTeacher=DeepSeek-R1, Training Dataset=BOBA-2002026.01 | 76.67 | 68.54 | 72.61 | |
| RRTTeacher=DeepSeek-R1, Training Dataset=S1K-2002026.01 | 76.67 | 70.63 | 73.65 | |
| T3STeacher=QWQ, Training Dataset=S1K-2002026.01 | 76.67 | 72.5 | 74.59 | |
| RRTTeacher=QWQ, Training Dataset=BOBA-2002026.01 | 76.04 | 69.17 | 72.61 | |
| BASETraining Dataset=BOBA-2002026.01 | 75.83 | 67.08 | 71.46 | |
| BASETraining Dataset=S1K-2002026.01 | 75.83 | 67.08 | 71.46 | |
| RRTTeacher=QWQ, Training Dataset=S1K-2002026.01 | 75 | 71.67 | 73.33 | |
| SFTTeacher=QWQ, Training Dataset=BOBA-2002026.01 | 73.33 | 68.33 | 70.83 | |
| SFTTeacher=QWQ, Training Dataset=S1K-2002026.01 | 73.33 | 63.33 | 68.33 | |
| SFTTeacher=DeepSeek-R1, Training Dataset=S1K-2002026.01 | 72.5 | 55.83 | 64.17 | |
| SFTTeacher=DeepSeek-R1, Training Dataset=BOBA-2002026.01 | 71.25 | 55 | 63.13 | |
| -T3STeacher=QWQ, Training Dataset=BOBA-2002026.01 | 50 | 33.33 | 41.67 | |
| -T3STeacher=QWQ, Training Dataset=S1K-2002026.01 | 46.67 | 40 | 43.33 | |
| -T3STeacher=DeepSeek-R1, Training Dataset=BOBA-2002026.01 | 30.63 | 25.63 | 28.13 | |
| -T3STeacher=DeepSeek-R1, Training Dataset=S1K-2002026.01 | 26.67 | 26.67 | 26.67 |