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

Purpose: We present an updated study evaluating the performance of large language models (LLMs) in answering radiation oncology physics questions, focusing on the latest released models. Methods: A set of 100 multiple-choice radiation oncology physics questions, previously created by us, 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 exams. To evaluate their deductive reasoning abilities, the correct answer options in the questions were replaced with "None of the above." Then, the explain-first and step-by-step instruction prompt was used to test if it improved their reasoning abilities. The performance of the LLMs was compared to medical physicists in majority-vote scenarios. Results: All models demonstrated expert-level performance on these questions, with o1-preview even surpassing medical physicists in majority-vote scenarios. When substituting 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 prompt helped enhance the reasoning abilities of LLaMA 3.1 (405B), Gemini 1.5 Pro, and Claude 3.5 Sonnet models. Conclusion: These latest LLMs demonstrated expert-level performance in answering radiation oncology physics questions, exhibiting great potential for assisting in radiation oncology physics education.