List your company

Math Reasoning on AIME 2025 (pass@1 and pass@4)

0.63Pass@1XRPO
0.51560.54530.5750.6047Oct 8, 2025

Evaluation results

MethodLinks
XRPOModel=Llama-3.2-3B2025.100.632.38
GRPOModel=Llama-3.2-3B2025.100.521.97