List your company

Conformal Hallucination Detection on Diverse Benchmarks Aggregated (test)

98.5R-CovACSE
80.09284.87189.6594.429May 5, 2026

Evaluation results

MethodLinks
ACSEalpha=0.05 (Strict)2026.0598.51.322.497.155.44.4
CAPalpha=0.05 (Strict)2026.0595.31.723.895.146.14.6
DDCRP-CPalpha=0.05 (Strict)2026.0594.11.954.694.242.53.8
ACSEalpha=0.10 (Standard)2026.0593.91.07392.375.88.8
DDCRP-CPalpha=0.10 (Standard)2026.0592.31.455.188.462.87.6
CAPalpha=0.10 (Standard)2026.0590.21.324.291.765.49.3
ACSEalpha=0.20 (Permissive)2026.0584.21.084.583.589.417.8
CAPalpha=0.20 (Permissive)2026.0582.71.156.281.482.518.8
SUalpha=0.05 (Strict)2026.0582.31.058.18134.26.4
SUalpha=0.10 (Standard)2026.0581.61.028.98252.111.8
DDCRP-CPalpha=0.20 (Permissive)2026.05811.227.479.179.115.2
SUalpha=0.20 (Permissive)2026.0580.81.0111.585.268.422.5