Report
OpenAI’s o1 reportedly went 10 for 10 on medical case studies
A post quotes Thrive Capital’s Dr. Nworah Ayogu estimating that he and his colleagues might get two in ten right.
TLDR
A post says Thrive Capital’s Dr. Nworah Ayogu tested OpenAI’s reasoning models on New England Journal of Medicine case studies it describes as “House M.D.-level.” It quotes him saying “OpenAI & o1 was batting 10 out of 10”; he estimated that he and his colleagues might get two out of ten right.
Combined views
1 Source, first seen ago
