List your company

Mathematical Reasoning on MATH 500 (Avg@32, Pass@32)

86Avg@32MASPO
71.12874.98978.8582.711Feb 19, 2026

Evaluation results

MethodLinks
MASPOBackbone=DeepSeek-R1-Distill-Qwen-7B2026.028694.7
SAPOBackbone=DeepSeek-R1-Distill-Qwen-7B2026.0285.592.9
Clip HigherBackbone=DeepSeek-R1-Distill-Qwen-7B2026.0285.395.4
DACBackbone=DeepSeek-R1-Distill-Qwen-7B2026.0285.194.8
BAPOBackbone=DeepSeek-R1-Distill-Qwen-7B2026.028594.5
GRPOBackbone=DeepSeek-R1-Distill-Qwen-7B2026.0284.892.4
Entropy Adv.Backbone=DeepSeek-R1-Distill-Qwen-7B2026.0284.892.5
SAPOBackbone=DeepSeek-R1-Distill-Qwen-1.5B2026.0279.191.4
Entropy Adv.Backbone=DeepSeek-R1-Distill-Qwen-1.5B2026.0278.589.7
DACBackbone=DeepSeek-R1-Distill-Qwen-1.5B2026.0278.192.5
MASPOBackbone=DeepSeek-R1-Distill-Qwen-1.5B2026.027889.7
GRPOBackbone=DeepSeek-R1-Distill-Qwen-1.5B2026.0277.690.8
BAPOBackbone=DeepSeek-R1-Distill-Qwen-1.5B2026.0274.991
Clip HigherBackbone=DeepSeek-R1-Distill-Qwen-1.5B2026.0271.788.6