[ExI] Staying Healthy for the Singularity

[BillK]

GPT-5 Surpasses Doctors in Medical Reasoning Benchmarks
A new study from Emory University shows OpenAI’s GPT-5 outperforming
both GPT-4o and medical professionals on clinical reasoning and
multimodal diagnostic benchmarks.
Alicia Shapiro     Aug 18, 2025

<https://www.ainews.com/p/gpt-5-surpasses-doctors-in-medical-reasoning-benchmarks>
Quote:
The Emory University team tested GPT-5 against both AI predecessors
and medical professionals across a series of reasoning benchmarks.

On MedQA, a dataset modeled on U.S. medical licensing exam questions,
GPT-5 achieved 95.84% accuracy. In effect, this test serves as the
closest AI equivalent to a doctor’s board exam, making the result
especially significant. GPT-4o, the previous best model, scored
91.04%.

In expert-level tests, GPT-5 also outpaced pre-licensed medical
professionals. It performed +24.23% better in reasoning and +29.40%
better in understanding.
--------------------

So, ChatGPT-5 is now usually as good as a doctor.
This means you should check medical problems with ChatGPT-5. Even if
only to teach you what questions to ask your doctor.
But remember, ChatGPT-5 is not 100% infallible. If you are unlucky
enough to encounter a rare medical problem, it might make an error.

And keep exercising!  :)

BillK