F
fertrevino
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: From GPT-4 to GPT-5: Measuring progress through MedHELM [pdf] | Hacker News
Points: 85
# Comments: 57
Continue reading...
I found this to be an interesting finding. Here are the detailed results: https://www.fertrevino.com/docs/gpt5_medhelm.pdf
Comments URL: From GPT-4 to GPT-5: Measuring progress through MedHELM [pdf] | Hacker News
Points: 85
# Comments: 57
Continue reading...