Medical visual question answering built from PubMed Central figures at large scale.

PMC-VQA is a benchmark in healthcare AI. Medical visual question answering built from PubMed Central figures at large scale. Scores are reported as: Percent accuracy.

Audited by MedCheckZhang et al., 2024

Key facts

What it measuresMedical visual question answering built from PubMed Central figures at large scale.
Who should careVision-language teams needing volume.
Use it whenLarge-scale medical VQA training and evaluation.
Do not use it forClinical deployment decisions. Figures are not clinical images.
Score scalePercent accuracy.
Grader methodunknown
First released2024
LanguagesEnglish
Use casesimaging, research
CitationZhang et al., 2024
Statusactive

Paper

Frequently asked questions

What does PMC-VQA measure?

Medical visual question answering built from PubMed Central figures at large scale.

Who should use PMC-VQA?

Vision-language teams needing volume. Large-scale medical VQA training and evaluation.

What should PMC-VQA not be used for?

Clinical deployment decisions. Figures are not clinical images.

How are PMC-VQA scores reported?

Percent accuracy. Scores from different benchmarks are not comparable to each other.

Is PMC-VQA independent?

No conflicts of interest have been verified for PMC-VQA in this registry as of 2026-08-05. Absence of a recorded conflict means none has been verified, not that none exists.

Compare with

Asclepius

Spectrum evaluation for multimodal medical models across many imaging modalities and difficulty levels.

CheXpert

A large chest radiograph dataset with uncertainty labels and expert comparison. Predates language models and i

EndoBench

Multimodal evaluation for endoscopy image and video analysis.

GMAI-MMBench

Large multimodal benchmark for general medical AI, spanning many imaging modalities, departments and task type

MMMU (Health and Medicine)

The health and medicine subset of a broad expert-level multimodal reasoning benchmark.

OmniMedVQA

Very large medical visual question answering set spanning many modalities and anatomical regions.

Last verified 2026-08-05. Governance and conflict data compiled by Healthcare Discovery from primary sources, each linked above. Seed inventory from Ma et al., Beyond the Leaderboard, ACL 2026. How we verify · All 63 entities