Benchmark Radar™
Star —

ClinHallu Benchmark

Explore score history ↗

ClinHallu is a benchmark for diagnosing stage-wise hallucinations in medical multimodal large language models. It contains 7,031 instances with structured reasoning traces decomposed into visual recognition, knowledge recall, and reasoning integration, along with stage-replacement interventions for measuring final answer changes.

Released
2026-06-12
Evaluates
Biology & Drug Discovery, Reasoning, Vision & 3D
Openness
unknown
Importer
Claire Radar
Review status
unreviewed

ClinHallu paper and code

No reported scores are on record for this benchmark yet.

Which sources cite ClinHallu?

Related Biology & Drug Discovery, Reasoning, Vision & 3D benchmarks