112,120 frontal-view chest X-ray images from 30,805 unique patients with 14 disease labels extracted using NLP from radiology reports. Foundational benchmark for chest X-ray AI.
Auroc is the reported evaluation metric for NIH ChestX-ray14. 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
| Rank | Model | Trust | Score | Year | Links | Edit |
|---|---|---|---|---|---|---|
| 01 | TorchXRayVision | unverified | 85.8 | 2025 | Source ↗ | Edit result |
| 02 | chexnet | paper | 84.1 | 2025 | Source ↗ | Edit result |
| 03 | DenseNet-121 (Chest X-ray) | paper | 82.6 | 2025 | Source ↗ | Edit result |
| 04 | densenet-121-cxr | paper | 82.6 | 2025 | Source ↗ | Edit result |
| 05 | ResNet-50 (Chest X-ray) | paper | 80.4 | 2025 | Source ↗ | Edit result |
| 06 | resnet-50-cxr | paper | 80.4 | 2025 | Source ↗ | Edit result |