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

Step-level hallucination detection research benchmarks · SOTA2 Research

Step-level hallucination detection

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

0.965AUROC

6

May 14, 2026

99.8AUROC

6

May 14, 2026

91AUROC

6

May 14, 2026

Popular datasets

TruthfulQA PROCESSBENCH PRM800K

Follow for updates

Join SOTA2 Contact