chexpert
Unknown
OCR benchmark
7
Total Results
7
Models Tested
1
Metrics
2025-12-21
Last Updated
auroc
Higher is better
| Rank | Model | Score | Source |
|---|---|---|---|
| 1 | chexpert-auc-maximizer Mean AUC across 5 competition pathologies. Competition-winning ensemble. | 93 | stanford-leaderboard |
| 2 | biovil Microsoft's biomedical vision-language model. | 89.1 | microsoft-research |
| 3 | chexzero Zero-shot performance without task-specific training. Expert-level on multiple pathologies. | 88.6 | research-paper |
| 4 | gloria Global-Local Representations. Zero-shot evaluation. | 88.2 | research-paper |
| 5 | medclip Decoupled contrastive learning. Zero-shot transfer. | 87.8 | research-paper |
| 6 | torchxrayvision Pre-trained on multiple datasets. Strong transfer learning baseline. | 87.4 | github-readme |
| 7 | densenet-121-cxr Baseline DenseNet-121. Trained on CheXpert training set. | 86.5 | research-paper |