List your company

Mathematical Reasoning on AMC (Avg@32, Pass@32)

63.8Avg@32EntroAdv
31.45639.85348.2556.647Apr 13, 2026

Evaluation results

MethodLinks
EntroAdvBackbone=Qwen2.5-Math-7B, Method Category=Policy Entropy Method2026.0463.889.4
ForkingBackbone=Qwen2.5-Math-7B, Method Category=Policy Entropy Method2026.0463.786.6
EAPOBackbone=Qwen2.5-Math-7B, Method Category=Policy Entropy Method2026.0462.188.8
EntroRegBackbone=Qwen2.5-Math-7B, Method Category=Policy Entropy Method2026.0461.184.9
DAPOBackbone=Qwen2.5-Math-7B, Method Category=Classic RLVR Method2026.046184.8
KL-CovBackbone=Qwen2.5-Math-7B, Method Category=Policy Entropy Method2026.0459.285.9
GRPOBackbone=Qwen2.5-Math-7B, Method Category=Classic RLVR Method2026.0458.680.3
W-REINFBackbone=Qwen2.5-Math-7B, Method Category=Classic RLVR Method2026.0458.187.1
PRIMEBackbone=Qwen2.5-Math-7B, Method Category=Classic RLVR Method2026.0442.490.5
Base-7BBackbone=Qwen2.5-Math-7B, Method Category=Classic RLVR Method2026.0432.785.2