ChatGPT Versus DeepSeek: Assessing Artificial Intelligence Performance on Radiation Oncology Examination Questions
DeepSeek-R1 is less accurate and answers more slowly compared with ChatGPT o1, but is less costly at the time of this manuscript preparation. Careful analysis and consideration of the current landscape and performance of each model is needed before implementation of DeepSeek-R1 or ChatGPT o1 to determine if the added financial costs of ChatGPT o1 are within the intended goals of improved accuracy and efficiency.
Authors
- Ronald Chow (ORCID: https://orcid.org/0000-0001-6195-8624)
- Haibo Lin (ORCID: https://orcid.org/0000-0001-7476-0967)
- Gilmer Valdés (ORCID: https://orcid.org/0000-0002-5842-5410)
- M. A. Vermeulen (ORCID: https://orcid.org/0000-0001-6353-4729)
- Chenxi Gao (ORCID: https://orcid.org/0009-0007-2312-382X)
- Arpit M. Chhabra (ORCID: https://orcid.org/0000-0002-0604-0914)
- Charles B. Simone
- Francis T. S. Yu
- J. Isabelle Choi (ORCID: https://orcid.org/0009-0004-1273-5749)
- Ajay Zheng
- Irini Yacoub
Institutions
- University of Toronto (CA)
- Moffitt Cancer Center (US)
- University of Oxford (GB)
- New York Proton Center (US)
Publication Details
- Journal
- Advances in Radiation Oncology
- Published
- 2025-10-25
- DOI
- https://doi.org/10.1016/j.adro.2025.101929
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00