healthcare benchmark
CheXpert CXR
CheXpert is a large dataset of 224,316 chest radiographs from 65,240 patients for automated chest X-ray interpretation. The dataset includes uncertainty labels for 14 medical observations extracted from radiology reports. It serves as a benchmark for developing and evaluating automated chest radiograph interpretation models.
Updated Aug 11, 2026
Models1
Model coverage1
MetricScore
EvidenceB
CheXpert CXR Ranking
Higher score ranks better on this benchmark.
| 1 | GO | 48.1% | 100.0% | 1 | C |
CheXpert CXR Highlights
The leading models and scores on this benchmark.
What is CheXpert CXR?
What CheXpert CXR measures and how its scores work.
CheXpert is a large dataset of 224,316 chest radiographs from 65,240 patients for automated chest X-ray interpretation. The dataset includes uncertainty labels for 14 medical observations extracted from radiology reports. It serves as a benchmark for developing and evaluating automated chest radiograph interpretation models.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- CheXpert CXR
- Modality
- image
- Primary category
- healthcare
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- chexpert-cxr|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about CheXpert CXR.
Which model scores highest on CheXpert CXR?
MedGemma 4B IT is currently ranked first with 48.1%.
What does CheXpert CXR measure?
CheXpert is a large dataset of 224,316 chest radiographs from 65,240 patients for automated chest X-ray interpretation. The dataset includes uncertainty labels for 14 medical observations extracted from radiology reports. It serves as a benchmark for developing and evaluating automated chest radiograph interpretation models.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 model results are currently shown.
Does this benchmark affect the overall score?
No. This benchmark is shown for reference but does not contribute to the overall score.