List your company

Mathematical Reasoning on AIME Average

44.01Avg@32PMD-MEAN
12.591620.748328.90537.0617Feb 5, 2026

Evaluation results

MethodLinks
PMD-MEANBackbone=Qwen3-30B-A3B-Base, tau=0.1, Staleness=162026.0244.01
PMD-MEANBackbone=Qwen3-30B-A3B-Base, tau=0.01, Staleness=162026.0242.55
GRPOBackbone=Qwen3-30B-A3B-Base, tau=null, Staleness=162026.0232.24
PMD-MEANBackbone=Qwen2.5-7B, tau=0.005, Staleness=162026.0219.58
PMD-MEANBackbone=Qwen2.5-7B, tau=0.02, Staleness=162026.0219.58
On-policyBackbone=Qwen2.5-7B, tau=null, Staleness=12026.0218.49
PMD-MEANBackbone=Qwen2.5-7B, tau=0.01, Staleness=162026.0217.55
GRPOBackbone=Qwen2.5-7B, tau=null, Staleness=162026.0213.8