Expert-level pathology understanding and reasoning from slide images.

PathMMU is a benchmark in healthcare AI. Expert-level pathology understanding and reasoning from slide images. Scores are reported as: Percent accuracy on expert-level pathology items.

Audited by MedCheckSun et al., ECCV 2024

Key facts

What it measuresExpert-level pathology understanding and reasoning from slide images.
Who should careDigital pathology teams.
Use it whenPathology-specific model selection.
Do not use it forGeneral medical evaluation.
Score scalePercent accuracy on expert-level pathology items.
Grader methodunknown
First released2024
LanguagesEnglish
Use casesimaging, multimodal
CitationSun et al., ECCV 2024
Statusactive

Frequently asked questions

What does PathMMU measure?

Expert-level pathology understanding and reasoning from slide images.

Who should use PathMMU?

Digital pathology teams. Pathology-specific model selection.

What should PathMMU not be used for?

General medical evaluation.

How are PathMMU scores reported?

Percent accuracy on expert-level pathology items. Scores from different benchmarks are not comparable to each other.

Is PathMMU independent?

No conflicts of interest have been verified for PathMMU 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