Mathematical Reasoning on Math AIME26, HMMT (test)
69.3AIME 26 ScoreSelf-Verified Distillation
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Self-Verified DistillationBackbone=Qwen3-4B, Candidate generations (n)=8, Verification strength (v)=52026.05 | 69.3 | 46 | 8.4 | |
| Self-Verified DistillationBackbone=Qwen3-8B, Candidate generations (n)=8, Verification strength (v)=52026.05 | 64.7 | 48.7 | 4.6 | |
| Qwen3-8BModel size=8B2026.05 | 62 | 42.3 | — | |
| Qwen3-4BModel size=4B2026.05 | 59.3 | 39.3 | — | |
| Self-Verified DistillationBackbone=Qwen3-0.6B, Candidate generations (n)=8, Verification strength (v)=52026.05 | 12.7 | 10 | 3.2 | |
| Qwen3-0.6BModel size=0.6B2026.05 | 9.7 | 6.7 | — |