Performance of DeepSeek-R1, ChatGPT (GPT-o3-mini), and Gemini 2.0 Flash on German Medical Multiple-Choice Questions: Comparative Evaluation
Overall, DeepSeek demonstrates outstanding performance on German medical MCQs comparable to the widely used chatbots ChatGPT and Gemini. Similar to ChatGPT, DeepSeek's performance declined with increasing question length, highlighting verbosity as a persistent challenge for large language models. While DeepSeek's offline capability and lower operational costs are advantageous, its safe and reliable application in clinical contexts requires further investigation.
Authors
- A. Meyer (ORCID: https://orcid.org/0000-0002-8411-8799)
- Yassin Karay (ORCID: https://orcid.org/0009-0005-6380-158X)
- Andrea U. Steinbicker (ORCID: https://orcid.org/0000-0002-5237-961X)
- Remco Overbeek (ORCID: https://orcid.org/0000-0002-4046-0234)
- Thomas Streichert (ORCID: https://orcid.org/0000-0002-6588-720X)
Institutions
- University Hospital Cologne (DE)
Publication Details
- Journal
- JMIR Formative Research
- Published
- 2025-12-18
- DOI
- https://doi.org/10.2196/77357
- Citations
- 4
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 2.62