Skip to content

o1 in Medicine

A medical AI model studied across many datasets

Visit official site
Category AI models

What o1 in Medicine is

o1 in Medicine is described as an AI model for the medical field, developed by researchers from UC Santa Cruz, University of Edinburgh and National Institutes of Health.

What you can do with it

  • Read evaluation across 12 medical domains
  • Refer to the 73.3 percent average across 19 datasets
  • Compare results with and without CoT prompting on question answering
  • Review multilingual tasks and agent benchmarks
  • Study case comparisons with GPT-4 on answers and diagnosis suggestions

Pros & cons

✓ What we like

  • Multilingual tasks and agent benchmarks are named
  • Case studies compare o1 with GPT-4 on answers and diagnosis suggestions

! What to watch out for

  • Research and application are described as at an early stage
  • Results depend on the medical datasets and prompt strategies

FAQ

Who developed it?

Researchers from UC Santa Cruz, University of Edinburgh and National Institutes of Health are named.

What accuracy is listed?

The material states an average accuracy of 73.3 percent across 19 medical datasets.

Last reviewed: 2026-11-15

More LLM API platform tools

View all →

How we review