“Cambridge University academics tested ChatGPT 4 against the knowledge of medics at different stages of their career.

The AI program scored 69% when tested in a mock exam of 87 questions.

About 374 ophthalmology questions were used to train the ChatGPT 4.

Its answers were compared to five expert ophthalmologists—doctors who care for patients with eye conditions—three trainee ophthalmologists, and two unspecialised junior doctors…

Expert ophthalmologists achieved a median score of 76%, trainees scored 59% and junior doctors scored 43%.”

From BBC.