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

LLM Hallucination Detection research benchmarks · SOTA2 Research

LLM Hallucination Detection

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

ContextualJudgeBench

92Refusal Rate (Ans.)

20

Mar 26, 2026

HaluEval (random sample of 1,000 text pairs)

LAG-XAI (cheap geometric check)

95.3Recall

1

Apr 8, 2026

Popular datasets

HaluEval ContextualJudgeBench

Follow for updates

Join SOTA2 Contact