Who leads the MIMIC-CXR benchmark?

chexzero currently leads MIMIC-CXR with a score of 89.2 on auroc.

What is the state-of-the-art score on MIMIC-CXR?

The state-of-the-art result on MIMIC-CXR is 89.2 (auroc), achieved by chexzero as of 2026.

How many models are tracked on MIMIC-CXR?

Codesota tracks 3 models on MIMIC-CXR.

When was the MIMIC-CXR leaderboard last updated?

The MIMIC-CXR leaderboard on Codesota includes results through 2026.

Codesota · Benchmark · MIMIC-CXRHome/Leaderboards/MIMIC-CXR

Unknown

MIMIC-CXR.

Name: MIMIC-CXR Benchmark Results
Creator: Unknown
Published: 2026-01-01
License: https://creativecommons.org/licenses/by/4.0/

377,110 chest X-ray images from 227,835 studies of 65,379 patients with free-text radiology reports. Largest publicly available chest X-ray dataset with paired image-text data.

Paper ↗Leaderboard ↓

§ 01 · Leaderboard

Results by metric.

Only 3 models on this benchmark

Help build the community leaderboard — submit your model results.

Found a wrong score or missing run?

Use row edits to send a sourced correction into moderation.

Add / edit result ↗Report issue ↗

auroc

Auroc is the reported evaluation metric for MIMIC-CXR. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.

Higher is better

Trust tiers for aurocverifiedpapervendorcommunityunverified

Muted rows were not state of the art when published — an earlier or same-year result already scored better.

Rank	Model	Trust	Score	Year	Links	Fix
01	chexzero Non-API entry from src	unverified	89.2	2026	N/A	Looks wrong?
02	torchxrayvision Non-API entry from src	unverified	86.3	2026	N/A	Looks wrong?
03	convirt Non-API entry from src	unverified	85.7	2026	N/A	Looks wrong?

§ 04 · Submit a result

Add to the leaderboard.

Submit a Result

← Back to Leaderboards