Mathematical Reasoning on Olympiad (Avg@8, Pass@8, Length)
17.26Avg@8PowerOPD
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| PowerOPDTeacher=Qwen3-8B, Student=Qwen3-0.6B-Base, Class=PowerOPD, alpha=0.52026.06 | 17.26 | 36.89 | 2,552 | |
| PowerOPDTeacher=Qwen3-8B, Student=Qwen3-0.6B-Base, Class=PowerOPD, alpha=12026.06 | 17.24 | 36.3 | 2,637 | |
| PowerOPDTeacher=Qwen3-8B, Student=Qwen3-0.6B-Base, Class=PowerOPD, alpha=102026.06 | 17.24 | 36 | 2,523 | |
| PowerOPDTeacher=Qwen3-8B, Student=Qwen3-0.6B-Base, Class=PowerOPD, alpha=1002026.06 | 17.17 | 34.07 | 2,331 | |
| PowerOPDTeacher=Qwen3-8B, Student=Qwen3-0.6B-Base, Class=PowerOPD, alpha=52026.06 | 17.13 | 35.11 | 2,566 | |
| PowerOPDTeacher=Qwen3-8B, Student=Qwen3-0.6B-Base, Class=PowerOPD, alpha=502026.06 | 16.96 | 35.7 | 2,449 | |
| Vanilla + TanhTeacher=Qwen3-8B, Student=Qwen3-0.6B-Base, Class=Vanilla, Param=+ Tanh2026.06 | 16.89 | 34.52 | 2,698 | |
| PowerOPDTeacher=Qwen3-8B, Student=Qwen3-0.6B-Base, Class=PowerOPD, alpha=5002026.06 | 16.83 | 35.26 | 2,201 | |
| Vanilla + ClipTeacher=Qwen3-8B, Student=Qwen3-0.6B-Base, Class=Vanilla, Param=+ Clip2026.06 | 16.2 | 34.22 | 2,674 | |
| PowerOPDTeacher=Qwen3-8B, Student=Qwen3-0.6B-Base, Class=PowerOPD, alpha=0.12026.06 | 15.94 | 34.67 | 2,632 | |
| Vanilla + Z-ScoreTeacher=Qwen3-8B, Student=Qwen3-0.6B-Base, Class=Vanilla, Param=+ Z-Score2026.06 | 15.54 | 35.7 | 2,528 | |
| VanillaTeacher=Qwen3-8B, Student=Qwen3-0.6B-Base, Class=Vanilla2026.06 | 14.35 | 33.33 | 2,708 | |
| Full-vocabTeacher=Qwen3-8B, Student=Qwen3-0.6B-Base, Class=Full-vocab2026.06 | 6.62 | 21 | 4,096 |