Generalist Large Language Models Outperform Clinical Tools on Medical Benchmarks

TL;DR

This study compares clinical AI assistants and generalist large language models on medical benchmarks, finding that state-of-the-art LLMs outperform specialized clinical tools in accuracy and communication quality.

Contribution

It provides the first independent, quantitative evaluation showing that generalist LLMs surpass clinical AI tools on medical benchmarks, highlighting the need for rigorous assessment.

Findings

GPT-5 achieved the highest scores among models.

Clinical tools showed deficits in completeness and safety reasoning.

Generalist LLMs outperformed clinical AI systems on benchmarks.

Abstract

Specialized clinical AI assistants are rapidly entering medical practice, often framed as safer or more reliable than general-purpose large language models (LLMs). Yet, unlike frontier models, these clinical tools are rarely subjected to independent, quantitative evaluation, creating a critical evidence gap despite their growing influence on diagnosis, triage, and guideline interpretation. We assessed two widely deployed clinical AI systems (OpenEvidence and UpToDate Expert AI) against three state-of-the-art generalist LLMs (GPT-5, Gemini 3 Pro, and Claude Sonnet 4.5) using a 1,000-item mini-benchmark combining MedQA (medical knowledge) and HealthBench (clinician-alignment) tasks. Generalist models consistently outperformed clinical tools, with GPT-5 achieving the highest scores, while OpenEvidence and UpToDate demonstrated deficits in completeness, communication quality, context awareness, and systems-based safety reasoning. These findings reveal that tools marketed for clinical decision support may often lag behind frontier LLMs, underscoring the urgent need for transparent, independent evaluation before deployment in patient-facing workflows.