List your company

Mathematical Reasoning on AMC 2023 (test) (Avg@8)

68.7Avg@8 Success RateDIFF
52.47656.68860.965.112May 26, 2026

Evaluation results

MethodLinks
DIFFModel=Qwen2.5-Math-7B, Evaluation Step=9002026.0568.7
GAINRLModel=Qwen2.5-Math-7B, Evaluation Step=9002026.0568.4
SAERLGModel=Qwen2.5-Math-7B, Evaluation Step=9002026.0568.4
GRPOModel=Qwen2.5-Math-7B, Evaluation Step=9002026.0568.1
ADARFTModel=Qwen2.5-Math-7B, Evaluation Step=9002026.0563.1
SAERLGModel=Qwen2.5-Math-1.5B, Evaluation Step=9002026.0556.2
SAERLDModel=Qwen2.5-Math-1.5B, Evaluation Step=9002026.0555.9
DAPOModel=Qwen2.5-Math-1.5B, Evaluation Step=9002026.0555.6
ADARFTModel=Qwen2.5-Math-1.5B, Evaluation Step=9002026.0555.6
DIFFModel=Qwen2.5-Math-1.5B, Evaluation Step=9002026.0555
GRPOModel=Qwen2.5-Math-1.5B, Evaluation Step=9002026.0553.4
GAINRLModel=Qwen2.5-Math-1.5B, Evaluation Step=9002026.0553.1