Evaluation of the accuracy of large language models in answering bone cancer-related questions
When answering bone cancer-related questions, Deepseek V3.1, ChatGPT 5, and Grok 4 generally performed well. Specifically, when responding to questions about Ewing sarcoma, ChatGPT 5 and Grok 4 demonstrated higher accuracy than Deepseek V3.1. While each model has its own strengths and limitations, their collective potential to enhance medical knowledge and improve healthcare outcomes is undeniable.
Authors
- S. Ye (ORCID: https://orcid.org/0009-0002-4302-4427)
- Feng Lin (ORCID: https://orcid.org/0000-0001-9929-8721)
- Liping Huang (ORCID: https://orcid.org/0000-0003-1623-3397)
- Qi Pan (ORCID: https://orcid.org/0009-0009-9381-5826)
- Ning Liu (ORCID: https://orcid.org/0000-0003-0884-0058)
Institutions
- Ganzhou People's Hospital (CN)
Publication Details
- Journal
- Frontiers in Public Health
- Published
- 2025-12-05
- DOI
- https://doi.org/10.3389/fpubh.2025.1719047
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00