Who leads the CheXpert benchmark?

chexpert-auc-maximizer currently leads CheXpert with a score of 93 on auroc.

What is the state-of-the-art score on CheXpert?

The state-of-the-art result on CheXpert is 93 (auroc), achieved by chexpert-auc-maximizer as of 2025.

How many models are tracked on CheXpert?

Codesota tracks 9 models on CheXpert.

When was the CheXpert leaderboard last updated?

The CheXpert leaderboard on Codesota includes results through 2025.

Codesota · Benchmark · CheXpertHome/Leaderboards/CheXpert

Unknown

CheXpert.

Name: CheXpert Benchmark Results
Creator: Unknown
Published: 2025-01-01
License: https://creativecommons.org/licenses/by/4.0/

224,316 chest radiographs from 65,240 patients with 14 pathology labels. Includes uncertainty labels and expert radiologist annotations for validation set. The gold standard for chest X-ray classification.

Paper ↗Leaderboard ↓

§ 01 · Leaderboard

Results by metric.

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 CheXpert. 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

Rank	Model	Trust	Score	Year	Links	Edit
01	chexpert-auc-maximizer Mean AUC across 5 competition pathologies. Competition-winning ensemble.	paper	93	2025	Source ↗	Edit result
02	CheXpert AUC Maximizer Mean AUC across 5 competition pathologies. Competition-winning ensemble.	unverified	93	2025	Source ↗	Edit result
03	BioViL Microsoft's biomedical vision-language model.	unverified	89.1	2025	Source ↗	Edit result
04	chexzero Zero-shot performance without task-specific training. Expert-level on multiple pathologies.	paper	88.6	2025	Source ↗	Edit result
05	GLoRIA Global-Local Representations. Zero-shot evaluation.	paper	88.2	2025	Source ↗	Edit result
06	MedCLIP Decoupled contrastive learning. Zero-shot transfer.	paper	87.8	2025	Source ↗	Edit result
07	TorchXRayVision Pre-trained on multiple datasets. Strong transfer learning baseline.	unverified	87.4	2025	Source ↗	Edit result
08	DenseNet-121 (Chest X-ray) Baseline DenseNet-121. Trained on CheXpert training set.	paper	86.5	2025	Source ↗	Edit result
09	densenet-121-cxr Baseline DenseNet-121. Trained on CheXpert training set.	paper	86.5	2025	Source ↗	Edit result

§ 04 · Submit a result

Add to the leaderboard.

← Back to Leaderboards