List your company

Math Reasoning on AIME 2025 (test) (pass@1)

50Pass@1 RateMerged (α=0.2)
22.23229.44136.6543.859Apr 12, 2026

Evaluation results

MethodLinks
Merged (α=0.2)Model variant=Merged (α=0.2), Interpolation Weight=0.22026.0450
Qwen3-4B-Instruct-2507Model variant=Base Model2026.0446.7
SFT No-TestModel variant=SFT No-Test2026.0423.3