multimodal benchmark
MIMIC CXR is a publicly available dataset of 377,110 de-identified chest radiograph images corresponding to 227,835 studies from 65,379 patients at Beth Israel Deaconess Medical Center, with free-text radiology reports.
Updated Sep 5, 2026
Higher score ranks better on this benchmark.
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelGO | Score88.90% | Percentile100.00% | Participants1 | EvidenceC | Evaluated |
The leading models and scores on this benchmark.
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis mimic cxr AI model leaderboard uses descending score in the benchmark original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
Selection summary
MedGemma 4B IT currently leads MIMIC CXR with 88.90%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price, and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
What MIMIC CXR measures and how its scores work.
MIMIC CXR is a multimodal dataset used in medical imaging research, automated report generation, and medical AI development.
The benchmark reports a Score in ratio units; the input does not specify what the score measures.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
Common questions about MIMIC CXR.
MedGemma 4B IT is currently ranked first with 88.90%.
The current leaders are MedGemma 4B IT (88.90%).
No matched official input price is currently available.
No matched runtime record is currently available.
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.
The benchmark reports a Score in ratio units; the input does not specify what the score measures.
Yes. Higher values rank better for this benchmark.
1 model results are currently shown.
No. This benchmark is shown for reference but does not contribute to the overall score.