List your company

Mathematical Reasoning on AMC (pass@1/mean@32)

71.2Pass@1 Score (mean@32)p*
62.67264.88667.169.314Apr 30, 2026

Evaluation results

MethodLinks
p*Setting=GRPO2026.0471.2
p* smooth(alpha = 0.01)Setting=GRPO2026.0468.1
p* smooth(alpha = 0.01)Setting=ZVF2026.0468
No samplingSetting=ZVF2026.0464.7
No samplingSetting=GRPO2026.0464.1
p*Setting=ZVF2026.0463