Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Response-level Hallucination Detection research benchmarks · SOTA2 Research

Response-level Hallucination Detection

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

RAGTruth (test)

GASP-threshold (default)

74.5AUC

15

Jul 7, 2026

94.91AUROC

13

Apr 20, 2026

LettuceDetect-L

91.89AUROC

13

Apr 20, 2026

HallucinationProbes

76.3AUROC

11

Apr 20, 2026

Popular datasets

RAGTruth RAGognize HDM-Bench

Follow for updates

Join SOTA2 Contact