List your company

Mathematical Reasoning on GSM8K (ECR, GSC, APSS)

96.42ECRTopK
94.75695.18895.6296.052Mar 28, 2026

Evaluation results

MethodLinks
TopKalpha (α)=0.05, sample candidates per prompt (N)=5, feature map / quadratic basis (Φ(X))=[1, T(X), T(X)^2], verifier loss type (T(X))=mean verifier loss2026.0396.4286.521
CFC-P-Falpha (α)=0.05, sample candidates per prompt (N)=5, feature map / quadratic basis (Φ(X))=[1, T(X), T(X)^2], verifier loss type (T(X))=mean verifier loss2026.0395.2488.794.59
ICPalpha (α)=0.05, sample candidates per prompt (N)=5, feature map / quadratic basis (Φ(X))=[1, T(X), T(X)^2], verifier loss type (T(X))=mean verifier loss2026.0395.0979.854.73
Learnt CPalpha (α)=0.05, sample candidates per prompt (N)=5, feature map / quadratic basis (Φ(X))=[1, T(X), T(X)^2], verifier loss type (T(X))=mean verifier loss2026.0394.9188.484.01
CFCalpha (α)=0.05, sample candidates per prompt (N)=5, feature map / quadratic basis (Φ(X))=[1, T(X), T(X)^2], verifier loss type (T(X))=mean verifier loss2026.0394.8288.482.35