List your company

Mathematical Reasoning on AIME24 (Avg@32)

35.1Avg@32MHPO
14.319.725.130.5Mar 14, 2026

Evaluation results

MethodLinks
MHPOBackbone=Qwen2.5-Math-7B-Instruct2026.0335.1
DAPOBackbone=Qwen2.5-Math-7B-Instruct2026.0331.2
GRPOBackbone=Qwen2.5-Math-7B-Instruct2026.0330.8
GSPOBackbone=Qwen2.5-Math-7B-Instruct2026.0330.1
SAPOBackbone=Qwen2.5-Math-7B-Instruct2026.0330
BaselineBackbone=Qwen2.5-Math-7B-Instruct2026.0315.1