List your company

Mathematical Reasoning on GSM8K (test) (Avg@8)

91.5Accuracy (Avg@8)SAERLG
78.39681.79885.288.602May 26, 2026

Evaluation results

MethodLinks
SAERLGModel=Qwen2.5-Math-7B, Evaluation Step=9002026.0591.5
DIFFModel=Qwen2.5-Math-7B, Evaluation Step=9002026.0590.9
GRPOModel=Qwen2.5-Math-7B, Evaluation Step=9002026.0590.3
GAINRLModel=Qwen2.5-Math-7B, Evaluation Step=9002026.0590.1
ADARFTModel=Qwen2.5-Math-7B, Evaluation Step=9002026.0587.5
SAERLDModel=Qwen2.5-Math-1.5B, Evaluation Step=9002026.0584.6
SAERLGModel=Qwen2.5-Math-1.5B, Evaluation Step=9002026.0583.5
DAPOModel=Qwen2.5-Math-1.5B, Evaluation Step=9002026.0581.9
DIFFModel=Qwen2.5-Math-1.5B, Evaluation Step=9002026.0581.6
GRPOModel=Qwen2.5-Math-1.5B, Evaluation Step=9002026.0581.1
GAINRLModel=Qwen2.5-Math-1.5B, Evaluation Step=9002026.0579.2
ADARFTModel=Qwen2.5-Math-1.5B, Evaluation Step=9002026.0578.9