Mathematical Reasoning on AIME 24 (Pass@8, Avg@8)
5Avg@8Full-vocab
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Full-vocabTeacher=Qwen3-8B, Student=Qwen3-0.6B-Base, Class=Full-vocab2026.06 | 5 | 6.67 | 4,096 | |
| PowerOPDTeacher=Qwen3-8B, Student=Qwen3-0.6B-Base, Class=PowerOPD, alpha=5002026.06 | 5 | 6.67 | 3,059 | |
| PowerOPDTeacher=Qwen3-8B, Student=Qwen3-0.6B-Base, Class=PowerOPD, alpha=0.12026.06 | 3.75 | 13.33 | 3,413 | |
| Vanilla + TanhTeacher=Qwen3-8B, Student=Qwen3-0.6B-Base, Class=Vanilla, Param=+ Tanh2026.06 | 2.92 | 10 | 3,518 | |
| PowerOPDTeacher=Qwen3-8B, Student=Qwen3-0.6B-Base, Class=PowerOPD, alpha=52026.06 | 2.92 | 6.67 | 3,512 | |
| PowerOPDTeacher=Qwen3-8B, Student=Qwen3-0.6B-Base, Class=PowerOPD, alpha=1002026.06 | 2.92 | 10 | 3,164 | |
| Vanilla + ClipTeacher=Qwen3-8B, Student=Qwen3-0.6B-Base, Class=Vanilla, Param=+ Clip2026.06 | 1.67 | 6.67 | 3,506 | |
| PowerOPDTeacher=Qwen3-8B, Student=Qwen3-0.6B-Base, Class=PowerOPD, alpha=0.52026.06 | 1.67 | 6.67 | 3,359 | |
| PowerOPDTeacher=Qwen3-8B, Student=Qwen3-0.6B-Base, Class=PowerOPD, alpha=12026.06 | 1.67 | 6.67 | 3,584 | |
| PowerOPDTeacher=Qwen3-8B, Student=Qwen3-0.6B-Base, Class=PowerOPD, alpha=502026.06 | 1.67 | 6.67 | 3,262 | |
| Vanilla + Z-ScoreTeacher=Qwen3-8B, Student=Qwen3-0.6B-Base, Class=Vanilla, Param=+ Z-Score2026.06 | 1.25 | 6.67 | 3,371 | |
| PowerOPDTeacher=Qwen3-8B, Student=Qwen3-0.6B-Base, Class=PowerOPD, alpha=102026.06 | 1.25 | 6.67 | 3,274 | |
| VanillaTeacher=Qwen3-8B, Student=Qwen3-0.6B-Base, Class=Vanilla2026.06 | 0.83 | 3.33 | 3,436 |