Performance of the Large Language Models on the Chinese National Nurse Licensure Examination: Cross-Sectional Evaluation Study.

JMIR Med Inform · 2025 · PMC12582878 · PMID 41184207

Europe PMC DOI

hedged sentences

0.3400

closest p · 6.8× alpha

0.3400

boldest claim

The sentences

did not reach statistical significanceP =.34not close (p > 0.1)

For the remaining LLMs, the differences in performance between the 2 sections did not reach statistical significance (minimum P =.34).

also in 111,027 other papers

an increasing trendno p-value reported

(2) In the Practical Skills section, DeepSeek V3 showed an increasing trend for both unique correct answers (3 and 6) and unique incorrect answers (2 and 3) between Attempt 1 and Attempt 2.

also in 63,971 other papers

Quoted from the open-access full text in Europe PMC under the licence the publisher applied. The sentence is reproduced exactly as published; the emphasis is ours.