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

Multi-image hallucination evaluation research benchmarks · SOTA2 Research

Multi-image hallucination evaluation

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

Qwen2.5-VL + CAPL

62Accuracy

12

Mar 10, 2026

GLM4.1VBase + CAPL

61.33Accuracy

12

Mar 10, 2026

Popular datasets

BLINK MuirBench

Follow for updates

Join SOTA2 Contact