Math Reasoning on AIME 2025 (test) (pass@1)
50Pass@1 RateMerged (α=0.2)
Evaluation Results
| Method | Links | |
|---|---|---|
| Merged (α=0.2)Model variant=Merged (α=0.2), Interpolation Weight=0.22026.04 | 50 | |
| Qwen3-4B-Instruct-2507Model variant=Base Model2026.04 | 46.7 | |
| SFT No-TestModel variant=SFT No-Test2026.04 | 23.3 |