September 16, 2025

Evaluation of DeepSeek-R1 and ChatGPT on the Chinese National Medical Licensing Examination: A Multi-Year Comparative Study

View Full Paper

Ask AI

Bookmark

DeepSeek-R1 outperformed ChatGPT significantly on the Chinese National Medical Licensing Examination.
Temporal analysis shows ChatGPT's accuracy declined from 2019 to 2021, while DeepSeek-R1 remained stable.
A generalized linear mixed model was used to analyze the performance of both models on the licensing exam's questions.
Findings emphasize the need for domain adaptation and robust evaluation of large language models in clinical contexts.

Discussion

No takes yet. Share an insight, caveat, or question.

Implication

A multi-year analysis shows DeepSeek-R1 outperforms ChatGPT on the Chinese National Medical Licensing Examination, indicating differences in model effectiveness.

Cite This Study

Wang et al. (2025) studied this question.

synapsesocial.com/papers/68d4565b31b076d99fa5b487 https://doi.org/10.21203/rs.3.rs-7380847/v1

View Full Paper

Ask AI

Bookmark

Implication

A multi-year analysis shows DeepSeek-R1 outperforms ChatGPT on the Chinese National Medical Licensing Examination, indicating differences in model effectiveness.

Evaluation of DeepSeek-R1 and ChatGPT on the Chinese National Medical Licensing Examination: A Multi-Year Comparative Study

Key Points

Discussion

Implication

Cite This Study

Evaluation of DeepSeek-R1 and ChatGPT on the Chinese National Medical Licensing Examination: A Multi-Year Comparative Study

Key Points

Discussion

Implication

Cite This Study

Also Consider

Also Consider