Benchmark

VQA-Rad Benchmark

What is VQA-Rad?

VQA-RAD (Visual Question Answering in Radiology) is the first manually constructed dataset of medical visual question answering containing 3,515 clinically…

Modality
multimodal
Evaluates
multimodal, image to text, healthcare, vision
Openness
unknown
Importer
LLM Stats
Reported scores
1

Source provenance

VQA-Rad results and reported scores

LLM Stats

ModelOrganizationReported valueReportedEvidence
MedGemma 4B ITGoogle0.4992025-05-20evidence

Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.

Which sources cite VQA-Rad?

Related multimodal, image to text, healthcare, vision benchmarks