List your company

Mathematical Reasoning on Minerva Math (Avg@4, Pass@4)

43.9Avg@4EAPO
13.11621.10829.137.092Apr 13, 2026

Evaluation results

MethodLinks
EAPOBackbone=Qwen2.5-Math-7B, Method Category=Policy Entropy Method2026.0443.957.3—
EntroRegBackbone=Qwen2.5-Math-7B, Method Category=Policy Entropy Method2026.0443.150.8—
ForkingBackbone=Qwen2.5-Math-7B, Method Category=Policy Entropy Method2026.044350.1—
DAPOBackbone=Qwen2.5-Math-7B, Method Category=Classic RLVR Method2026.0442.850.4—
EntroAdvBackbone=Qwen2.5-Math-7B, Method Category=Policy Entropy Method2026.0442.749.3—
KL-CovBackbone=Qwen2.5-Math-7B, Method Category=Policy Entropy Method2026.0440.954.1—
KL-CovMethod Category=Policy Entropy Method, Backbone=DeepScaleR-1.5B-8k2026.0440.550.256.5
EntroAdvMethod Category=Policy Entropy Method, Backbone=DeepScaleR-1.5B-8k2026.0440.446.256.3
EAPOMethod Category=Policy Entropy Method, Backbone=DeepScaleR-1.5B-8k2026.0439.749.157
GRPOMethod Category=Classic RLVR Method, Backbone=DeepScaleR-1.5B-8k2026.0439.44853.9
DAPOMethod Category=Classic RLVR Method, Backbone=DeepScaleR-1.5B-8k2026.0439.14855.1
ForkingMethod Category=Policy Entropy Method, Backbone=DeepScaleR-1.5B-8k2026.0438.748.653.7
GRPOBackbone=Qwen2.5-Math-7B, Method Category=Classic RLVR Method2026.0438.143.4—
W-REINFMethod Category=Classic RLVR Method, Backbone=DeepScaleR-1.5B-8k2026.0437.837.851.8
EntroRegMethod Category=Policy Entropy Method, Backbone=DeepScaleR-1.5B-8k2026.0437.647.551.9
Base-1.5BMethod Category=Classic RLVR Method, Backbone=DeepScaleR-1.5B-8k2026.0437.546.750.7
W-REINFBackbone=Qwen2.5-Math-7B, Method Category=Classic RLVR Method2026.0434.251.2—
PRIMEBackbone=Qwen2.5-Math-7B, Method Category=Classic RLVR Method2026.0415.737.8—
Base-7BBackbone=Qwen2.5-Math-7B, Method Category=Classic RLVR Method2026.0414.325.9—