From knowledge to judgment: A three-year longitudinal analysis of artificial intelligence large language model performance on the Chinese national nurse licensing examination
Xinju Zhan, Weihua Yu, Jianshu Cai, Jionghuang Chen · 2026
Read From knowledge to judgment: A three-year longitudinal analysis of artificial intelligence large language model performance on the Chinese national nurse licensing examination by Xinju Zhan, Weihua Yu, Jianshu Cai, Jionghuang Chen (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0353059.txt.
Description
Xinju Zhan and three colleagues present this 2026 PLOS One benchmark study testing fifteen leading language models on China's national nurse licensing examination across three years. Nearly ten thousand real exam questions were used, and models were only tested on exams released after the model itself, keeping the contest fair. Both Chinese and international models took part.
Performance climbed steeply: top accuracy rose from under half in 2022 to nearly four-fifths by 2025. Chinese-made models consistently beat international rivals, though the gap narrowed. Models handled knowledge questions better than applied clinical skills questions, and nearly half of the top models' remaining errors were failures of clinical judgment, like choosing the wrong nursing priority. The authors say passing an exam is not the same as thinking like a nurse.
Catalog record
| CREATOR | Xinju Zhan, Weihua Yu, Jianshu Cai, Jionghuang Chen |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 58368 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |