Does GPT-4 outperform ChatGPT on a mock neurosurgical written board examination?
GPT-4 significantly outperforms ChatGPT and achieves passing scores on a mock neurosurgical written board examination.
LLMs achieved passing scores on a mock 500-question neurosurgical written board examination, with GPT-4 significantly outperforming ChatGPT.
Ali et al. (Tue,) studied this question.