AUTHOR=Wang Peilong , Holmes Jason , Liu Zhengliang , Chen Dequan , Liu Tianming , Shen Jiajian , Liu Wei 

TITLE=A recent evaluation on the performance of LLMs on radiation oncology physics using questions of randomly shuffled options

JOURNAL=Frontiers in Oncology

VOLUME=Volume 15 - 2025

YEAR=2025

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2025.1557064

DOI=10.3389/fonc.2025.1557064

ISSN=2234-943X

ABSTRACT=PurposeWe present an updated study evaluating the performance of large language models (LLMs) in answering radiation oncology physics questions, focusing on the recently released models.MethodsA set of 100 multiple-choice radiation oncology physics questions, previously created by a well-experienced physicist, was used for this study. The answer options of the questions were randomly shuffled to create “new” exam sets. Five LLMs – OpenAI o1-preview, GPT-4o, LLaMA 3.1 (405B), Gemini 1.5 Pro, and Claude 3.5 Sonnet – with the versions released before September 30, 2024, were queried using these new exam sets. To evaluate their deductive reasoning ability, the correct answer options in the questions were replaced with “None of the above.” Then, the explain-first and step-by-step instruction prompts were used to test if this strategy improved their reasoning ability. The performance of the LLMs was compared with the answers from medical physicists.ResultsAll models demonstrated expert-level performance on these questions, with o1-preview even surpassing medical physicists with a majority vote. When replacing the correct answer options with ‘None of the above’, all models exhibited a considerable decline in performance, suggesting room for improvement. The explain-first and step-by-step instruction prompts helped enhance the reasoning ability of the LLaMA 3.1 (405B), Gemini 1.5 Pro, and Claude 3.5 Sonnet models.ConclusionThese recently released LLMs demonstrated expert-level performance in answering radiation oncology physics questions.