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
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 | torchxrayvision | unverified | 85.8 | 2026 | N/A | Looks wrong? |
| 02 | chexnet | unverified | 84.1 | 2026 | N/A | Looks wrong? |
| 03 | densenet-121-cxr | unverified | 82.6 | 2026 | N/A | Looks wrong? |
| 04 | resnet-50-cxr | unverified | 80.4 | 2026 | N/A | Looks wrong? |