MedNLI
by University of Massachusetts / Partners Healthcare · free · Last verified 2026-03-17
MedNLI is a clinical natural language inference dataset derived from MIMIC-III clinical notes, containing 14,049 sentence pairs annotated by clinicians for entailment, contradiction, and neutral relationships. It is the standard benchmark for NLI in the clinical domain and evaluates whether AI systems can reason about clinical text.
https://physionet.org/content/mednli/ ↗B
B—Above Average
Adoption: BQuality: AFreshness: BCitations: B+Engagement: F
Specifications
- License
- PhysioNet Credentialed Health Data License
- Pricing
- free
- Capabilities
- natural-language-inference, clinical-text-reasoning, clinical-nlp
- Integrations
- HuggingFace Datasets, AllenNLP
- Use Cases
- clinical-nlp-research, benchmark, model-evaluation
- API Available
- No
- Tags
- natural-language-inference, clinical-nlp, entailment, MIMIC, benchmark
- Added
- 2026-03-17
- Completeness
- 100%
Index Score
62.8Adoption
65
Quality
89
Freshness
60
Citations
76
Engagement
0
Put AI to work for your business
Deploy this dataset alongside autonomous AaaS agents that handle tasks end-to-end — no babysitting required.