Evaluating the Performance of DeepSeek-R1 and DeepSeek-V3 Versus OpenAI Models in the Chinese National Medical Licensing Examination: Cross-Sectional Comparative Study
This study demonstrates that DeepSeek-R1 and DeepSeek-V3 significantly outperform OpenAI models on the NMLE. DeepSeek models show promise as tools for medical education and exam preparation in the Chinese language.
Authors
- Jingxuan Fu (ORCID: https://orcid.org/0000-0003-4662-3396)
- Ke Hu (ORCID: https://orcid.org/0000-0003-1079-5137)
- Weiping Wang (ORCID: https://orcid.org/0000-0002-6619-1191)
- Yuchen Zhou (ORCID: https://orcid.org/0000-0002-8239-8619)
Institutions
- Capital Medical University (CN)
- Chinese Academy of Medical Sciences & Peking Union Medical College (CN)
- Peking Union Medical College Hospital (CN)
- Tsinghua University (CN)
Publication Details
- Journal
- JMIR Medical Education
- Published
- 2025-11-14
- DOI
- https://doi.org/10.2196/73469
- Citations
- 2
- Primary Topic
- Academic integrity and plagiarism
- Type
- article
- Field-Weighted Citation Impact
- 4.73