nih-chestxray14
Unknown
OCR benchmark
4
Total Results
4
Models Tested
1
Metrics
2025-12-21
Last Updated
auroc
Higher is better
| Rank | Model | Score | Source |
|---|---|---|---|
| 1 | torchxrayvision Multi-dataset pre-training improves over single-dataset. | 85.8 | github-readme |
| 2 | chexnet Original CheXNet on ChestX-ray14. Exceeded radiologist performance on pneumonia (0.768 vs 0.633). | 84.1 | research-paper |
| 3 | densenet-121-cxr Original NIH baseline model. | 82.6 | research-paper |
| 4 | resnet-50-cxr ResNet-50 baseline. | 80.4 | research-paper |