A large chest radiograph dataset with uncertainty labels and expert comparison. Predates language models and is an image classification benchmark.
Audited by MedCheckIrvin et al., AAAI 2019
Key facts
| What it measures | A large chest radiograph dataset with uncertainty labels and expert comparison. Predates language models and is an image classification benchmark. |
| Who should care | Radiology AI teams and anyone citing the imaging AI literature. |
| Use it when | Chest imaging model evaluation with an established expert baseline. |
| Do not use it for | Evaluating language models. It is not a text benchmark. |
| Score scale | AUC and expert radiologist comparison. |
| Grader method | unknown |
| First released | 2019 |
| Languages | English |
| Use cases | imaging |
| Citation | Irvin et al., AAAI 2019 |
| Status | active |
Frequently asked questions
What does CheXpert measure?
A large chest radiograph dataset with uncertainty labels and expert comparison. Predates language models and is an image classification benchmark.
Who should use CheXpert?
Radiology AI teams and anyone citing the imaging AI literature. Chest imaging model evaluation with an established expert baseline.
What should CheXpert not be used for?
Evaluating language models. It is not a text benchmark.
How are CheXpert scores reported?
AUC and expert radiologist comparison. Scores from different benchmarks are not comparable to each other.
Is CheXpert independent?
No conflicts of interest have been verified for CheXpert in this registry as of 2026-08-05. Absence of a recorded conflict means none has been verified, not that none exists.
Compare with
Spectrum evaluation for multimodal medical models across many imaging modalities and difficulty levels.
Multimodal evaluation for endoscopy image and video analysis.
Large multimodal benchmark for general medical AI, spanning many imaging modalities, departments and task type
The health and medicine subset of a broad expert-level multimodal reasoning benchmark.
Very large medical visual question answering set spanning many modalities and anatomical regions.
Expert-level pathology understanding and reasoning from slide images.
