NIH ChestX-ray14
Unknown
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.
Benchmark Stats
Models4
Papers4
Metrics1
SOTA History
Not enough data to show trend.
Only 4 models on this benchmark
Help build the community leaderboard — submit your model results.
auroc
auroc
Higher is better
| Rank | Model | Source | Score | Year | Paper |
|---|---|---|---|---|---|
| 1 | torchxrayvision Multi-dataset pre-training improves over single-dataset. | Editorial | 85.8 | 2025 | Source |
| 2 | chexnet Original CheXNet on ChestX-ray14. Exceeded radiologist performance on pneumonia (0.768 vs 0.633). | Editorial | 84.1 | 2025 | Source |
| 3 | densenet-121-cxr Original NIH baseline model. | Editorial | 82.6 | 2025 | Source |
| 4 | resnet-50-cxr ResNet-50 baseline. | Editorial | 80.4 | 2025 | Source |