Model card
CheXzero.
Harvard/MITopen-sourceCLIP-based Vision-LanguageMIT1 current SOTA
Zero-shot chest X-ray classification using CLIP. No task-specific training needed.
§ 01 · Benchmarks
Every benchmark CheXzero has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | MIMIC-CXR | Medical · Disease Classification | auroc | 89.2% | #1 | — | source ↗ |
| 02 | CheXpert | Medical · Disease Classification | auroc | 88.6% | #3 | — | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 05 · Sources & freshness
Where these numbers come from.
research-paper
2
results
0 of 2 rows marked verified.