GPT-5 achieves 76.5% accuracy on Japanese oral radiology board exam, surpassing earlier models

Generative AI model GPT-5 achieved 76.5% accuracy on Japan's oral and maxillofacial radiology board exam, significantly outperforming GPT-3.5 (40.3%) and GPT-4 (67.8%). It exceeded passing scores, especially on two-answer questions.

• GPT-5 accuracy was 76.5% (GPT-3.5: 40.3%, GPT-4: 67.8%) on the 2020–2022 JSOMR board-certification examinations.
• GPT-5 surpassed the passing threshold each year and showed significant gains over earlier models, particularly on two-answer questions.

Automated summary

RadPigeon summaries are original and for information only. They are not clinical advice.