Mathematical Reasoning on AIMO (Avg@16)
79.5Avg@16 AccuracyTeacher
Evaluation Results
| Method | Links | |
|---|---|---|
| TeacherBackbone=JustRL-1.5B2026.06 | 79.5 | |
| OPRD2026.06 | 79.1 | |
| OPD top-1Variant=sampled-token2026.06 | 77 | |
| OPD top-162026.06 | 76.5 | |
| StudentBackbone=R1-distill-1.5B2026.06 | 62.2 |