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

Hallucination Evaluation research benchmarks – Page 6 · SOTA2 Research

Hallucination Evaluation

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

AMBER-G (full discriminative split)

7.2CHAIR Score

2

May 15, 2026

COCO CHAIR evaluation (500 images) (val)

29.4CHAIRs Score

2

May 15, 2026

89Rand. Score

2

Mar 25, 2026

77Valid Nodes

2

Feb 26, 2026

Page 6 of 6

Popular datasets

POPE MME CHAIR Style-CHAIR HallusionBench

Follow for updates

Join SOTA2 Contact