From GPT-4 to GPT-5: Measuring Progress in Medical Language Understanding [pdf]

I recently worked on running a thorough healthcare eval on GPT-5. The results show a (slight) regression in GPT-5 performance compared to GPT-4 era models.

I found this to be an interesting finding. Here are the detailed results: https://www.fertrevino.com/docs/gpt5_medhelm.pdf

Comments URL: https://news.ycombinator.com/item?id=44979107

Points: 54

# Comments: 25

https://www.fertrevino.com/docs/gpt5_medhelm.pdf