List your company

Mathematical Reasoning on Hard Math Dataset

86MATH ScoreDAPO
82.46483.38284.385.218May 28, 2026

Evaluation results

MethodLinks
DAPOBackbone=R1-Dist-1.5B, Temperature=0.0 (except AIME/AMC: 0.1), avg@k=16 (AIME/AMC)2026.058679.331.653.271.825.472.562.560.3
DAPO + HistaBackbone=R1-Dist-1.5B, Temperature=0.0 (except AIME/AMC: 0.1), avg@k=16 (AIME/AMC)2026.058579.732.353.576.826.373.463.861.4
R1-Dist-1.5BTemperature=0.0 (except AIME/AMC: 0.1), avg@k=16 (AIME/AMC)2026.0582.676.429.752.272.52570.862.158.9