A 10-year-old CNN outperforms frontier LLMs for skin cancer diagnosis
A dermatologist reports that a 10-year-old convolutional neural network outperformed two state-of-the-art frontier LLMs in diagnosing skin cancer from clinical and dermoscopic images. The study suggests that specialized, older AI architectures may still hold advantages over general-purpose large language models in specific medical diagnostic tasks.
Why it matters
This highlights the limitations of general-purpose LLMs in high-stakes medical imaging and underscores the continued relevance of specialized, domain-specific AI models.
I am a dermatologist. I tested the ability of GPT-6 Astra and Claude Fable 5.1 to diagnosis skin cancer and found that they were less accurate than I expected. I compared to a 10-year old CNN and to my surprise found that this was superior.
By Dr Magnus Lynch 25 October 2026 5 min read
I showed these two images - a clinical photograph and a dermoscopic (skin microscope) image - to GPT-6 Astra and Claude Fable 5.1, two of the most capable AI models available in October 2026. Both said it was a seborrhoeic keratosis, a harmless warty growth, and that the patient could be discharged. I then showed them to fine-tuned version of Inception v3, a convolutional neural network (CNN) first published by Google in 2015 and fine-tuned here on public dermatology images. The CNN got the right answer based on the dermoscopy view.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in