List your company

Mathematical Reasoning on AIME25 (Avg@8, Pass@8, Response Length)

3.33Avg@8Full-vocab
0.30361.08931.8752.6607Jun 15, 2026

Evaluation results

MethodLinks
Full-vocabTeacher=Qwen3-8B, Student=Qwen3-0.6B-Base, Class=Full-vocab2026.063.336.674,096
PowerOPDTeacher=Qwen3-8B, Student=Qwen3-0.6B-Base, Class=PowerOPD, alpha=52026.063.3313.333,468
PowerOPDTeacher=Qwen3-8B, Student=Qwen3-0.6B-Base, Class=PowerOPD, alpha=5002026.062.0813.332,742
Vanilla + ClipTeacher=Qwen3-8B, Student=Qwen3-0.6B-Base, Class=Vanilla, Param=+ Clip2026.061.67103,711
Vanilla + TanhTeacher=Qwen3-8B, Student=Qwen3-0.6B-Base, Class=Vanilla, Param=+ Tanh2026.061.676.673,639
PowerOPDTeacher=Qwen3-8B, Student=Qwen3-0.6B-Base, Class=PowerOPD, alpha=1002026.061.25103,225
VanillaTeacher=Qwen3-8B, Student=Qwen3-0.6B-Base, Class=Vanilla2026.060.836.673,752
PowerOPDTeacher=Qwen3-8B, Student=Qwen3-0.6B-Base, Class=PowerOPD, alpha=0.12026.060.836.673,617
PowerOPDTeacher=Qwen3-8B, Student=Qwen3-0.6B-Base, Class=PowerOPD, alpha=0.52026.060.836.673,549
PowerOPDTeacher=Qwen3-8B, Student=Qwen3-0.6B-Base, Class=PowerOPD, alpha=12026.060.833.333,542
PowerOPDTeacher=Qwen3-8B, Student=Qwen3-0.6B-Base, Class=PowerOPD, alpha=102026.060.836.673,528
Vanilla + Z-ScoreTeacher=Qwen3-8B, Student=Qwen3-0.6B-Base, Class=Vanilla, Param=+ Z-Score2026.060.423.333,578
PowerOPDTeacher=Qwen3-8B, Student=Qwen3-0.6B-Base, Class=PowerOPD, alpha=502026.060.426.673,233