List your company

Mathematical Reasoning on MATH500 (Pass@1, Pass@8)

89.93Pass@1GRPO w/ MAPR
79.197281.983684.7787.5564Sep 26, 2025

Evaluation results

MethodLinks
GRPO w/ MAPRBase Model=Qwen3-14B2025.0989.9396.39
GRPOBase Model=Qwen3-14B2025.0988.7396.02
GRPO w/ MAPRBase Model=Qwen3-8B2025.0988.0595.35
GRPOBase Model=Qwen3-8B2025.0985.7594.31
GRPO w/ MAPRBase Model=Qwen3-4B2025.0984.5293.74
GRPOBase Model=Qwen3-4B2025.0979.6190.12