ArticleNature medicine2026
General-purpose large language models outperform specialized clinical AI tools on medical benchmarks.
Article in Nature medicine, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 18 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
18 citing papers in PubMed.
- The Promises and Perils of Clinical Decision Support Artificial Intelligence.The clinical teacher · 2026Article
- Article
- What Are Physicians For? How Psychiatry's Competencies Endure Into the Age of AI.Academic psychiatry : the journal of the American Association of Directors of Psychiatric Residency Training and the Association for Academic Psychiatry · 2026Article
- Development of a Framework for Evaluating Large Language Model Safety and Reliability: a Proof-of-Concept Evaluation.Journal of medical systems · 2026Article
- Article
- LungGPT: A unified multimodal system for interpretable diagnosis and clinical decision support of respiratory diseases.Cell reports. Medicine · 2026Article
- Multimodal Artificial Intelligence in Lung Cancer: From Data Integration to Precision Oncology.Cancers · 2026Review
- Artificial Intelligence for Clinical Decision Support in Rural Spine Care: A Narrative Review.Healthcare (Basel, Switzerland) · 2026Review
- AI-Based Spatial Burn Assessment with MLLMs: Body Region, 3 × 3 Grid Classification and Burn Instance Counting from Photographs and Semantic Segmentation Masks.Biomedicines · 2026Article
- Reply to: Limited benchmarks constrain the conclusions of a general-purpose versus clinical AI comparison.Nature medicine · 2026Article
- Reference quality of OpenEvidence across five medical specialties.npj health systems · 2026Article
- Structured prompting as reusable clinical tools.EULAR rheumatology open · 2026Article
- Large Language Models for Mental Health Prediction: Scoping Review of Bias and Clinical Utility Documentation in 2019-2024.JMIR AI · 2026Review
- Tutorial: guidance on the use of large language models for medical research.Nature protocols · 2026Review
- Medical AI has a measurement problem.Nature · 2026Article
- Gut Instincts, Machine Decisions: Evaluating AI Accuracy in the Diagnosis and Treatment of Disorders of Gut-Brain Interaction.Neurogastroenterology and motility · 2026Article
- Large language models for late-life depression: a blinded benchmark of clinical safety, geriatric appropriateness, and triage.Frontiers in psychiatry · 2026Article
- The Long road to AI-physician partnership starts with learners: a map for AI in medical education.BMJ digital health & AI · 2026Review
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
16 authors.
Funding
Abstract
Specialized clinical artificial intelligence (AI) tools are entering medical practice despite scarce independent evaluation. We quantitatively evaluate two clinical AI tools, OpenEvidence and UpToDate Expert AI, built on large language models (LLMs) against three frontier LLMs: GPT-5.2, Gemini 3.1 Pro and Claude Opus 4.6. Our evaluation has three stages: (1) 500 MedQA questions testing medical knowledge, (2) 500 HealthBench items measuring alignment with clinicians and (3) the real clinical queries (RCQ) benchmark, built from 100 de-identified queries from physicians to a general-purpose language model in a live clinical environment. For the RCQ benchmark, 12 US clinicians performed randomized, blinded review of model outputs, producing 1,800 model-question annotations. Frontier LLMs outperformed clinical AI tools in all three evaluations. Clinical AI tools performed comparably to auto-enabled Google Search AI Overview on the RCQ. These findings highlight the need for independent, real-world evaluation of AI tools before they enter clinical settings.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.