{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T09:35:54Z","timestamp":1793352954699,"version":"4.5.0"},"reference-count":40,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T00:00:00Z","timestamp":1783296000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To systematically evaluate the overall performance, subject-based differences, and question type adaptability of five mainstream large language models (ChatGPT, DeepSeek, Kimi, Qwen, and Doubao) in the Chinese National Pharmacist Licensing Examination (CNPLE), and to explore their feasibility as auxiliary tools for pharmaceutical examinations.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      A cross-sectional comparative study design was adopted. The practice questions of the 2024 CNPLE were used as the evaluation dataset, covering 480 standardized questions across four subjects: Pharmaceutical Professional Knowledge (I), Pharmaceutical Professional Knowledge (II), Comprehensive Knowledge and Skills of Pharmacy, and Pharmaceutical Administration and Regulation. The question types included Type A (single best choice), Type B (matching choice), Type C (comprehensive analysis), and Type X (multiple choice). Standardized prompts were used for independent tests using the official web versions of each model with default parameters. Each question was input separately in a new conversation session to avoid contextual interference. Taking the official standard answers as the gold standard, the subject accuracy rate, question type accuracy rate, and overall accuracy rate of each model were calculated. To compare the overall performance among the five models, Cochran\u2019s Q test was applied.\n                      <jats:italic>Post-hoc<\/jats:italic>\n                      pairwise comparisons were performed using McNemar\u2019s test with Bonferroni correction for multiple comparisons.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      All five models exceeded the 60% passing score threshold of the CNPLE. The overall accuracy ranking was: Kimi (89.58%) &amp;gt; Doubao (88.96%) &amp;gt; DeepSeek (87.29%) &amp;gt; Qwen (77.92%) &amp;gt; ChatGPT (72.50%). Cochran\u2019s Q test showed a statistically significant difference in the overall accuracy among the five models (\n                      <jats:italic>Q<\/jats:italic>\n                      = 111.39, df = 4,\n                      <jats:italic>P<\/jats:italic>\n                      &amp;lt; 0.001). Pairwise comparisons showed no significant differences among Kimi, Doubao and DeepSeek (\n                      <jats:italic>P<\/jats:italic>\n                      &amp;gt; 0.05), while all three performed significantly better than Qwen and ChatGPT (\n                      <jats:italic>P<\/jats:italic>\n                      &amp;lt; 0.001). At the subject level, all models achieved the best performance in Pharmaceutical Professional Knowledge (II) (average accuracy 89.50%) and relatively weak performance in Pharmaceutical Administration and Regulation (average accuracy 76.50%). At the question type level, Type C questions yielded the highest average accuracy (90.00%), whereas Type X questions had the lowest average accuracy (69.00%).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>In this single-run evaluation, the Chinese large language models tested achieved higher overall accuracy than ChatGPT under the same conditions. Among them, Kimi, Doubao and DeepSeek have reached an excellent performance level. Different models present differentiated advantages across subjects and question types. Regulatory subjects and Type X (multiple-answer) questions are common challenges for all models. The findings indicate that mainstream LLMs possess considerable potential as auxiliary tools for the CNPLE, and can provide intelligent support for pharmaceutical education and examination preparation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1880914","type":"journal-article","created":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T13:36:26Z","timestamp":1783344986000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["A comparative study of the performance of different large language models in the Chinese National Pharmacist Licensing Examination"],"prefix":"10.3389","volume":"13","author":[{"given":"Can","family":"Huang","sequence":"first","affiliation":[{"name":"Beijing Youan Hospital, Capital Medical University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanfang","family":"Sun","sequence":"additional","affiliation":[{"name":"Beijing Youan Hospital, Capital Medical University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing Youan Hospital, Capital Medical University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,6]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"3648","DOI":"10.1016\/j.cell.2025.05.018","article-title":"The generative era of medical AI.","volume":"188","author":"Fahrner","year":"2025","journal-title":"Cell"},{"key":"B2","doi-asserted-by":"publisher","first-page":"1134","DOI":"10.1038\/s41591-024-02855-5","article-title":"Adapted large language models can outperform medical experts in clinical text summarization.","volume":"30","author":"Van Veen","year":"2024","journal-title":"Nat Med"},{"key":"B3","doi-asserted-by":"publisher","first-page":"932","DOI":"10.1038\/s41591-024-03416-6","article-title":"A generalist medical language model for disease diagnosis assistance.","volume":"31","author":"Liu","year":"2025","journal-title":"Nat Med"},{"key":"B4","doi-asserted-by":"publisher","first-page":"101294","DOI":"10.1016\/j.ajpe.2024.101294","article-title":"Large language models and the North American Pharmacist Licensure Examination (NAPLEX) practice questions.","volume":"88","author":"Ehlert","year":"2024","journal-title":"Am J Pharm Educ"},{"key":"B5","doi-asserted-by":"publisher","first-page":"e73469","DOI":"10.2196\/73469","article-title":"Evaluating the performance of DeepSeek-R1 and DeepSeek-V3 versus OpenAI models in the Chinese National Medical Licensing Examination: cross-sectional comparative study.","volume":"11","author":"Wang","year":"2025","journal-title":"JMIR Med Educ"},{"key":"B6","doi-asserted-by":"publisher","first-page":"e63731","DOI":"10.2196\/63731","article-title":"Qwen-2.5 outperforms other large language models in the Chinese National Nursing Licensing Examination: retrospective cross-sectional comparative study.","volume":"13","author":"Zhu","year":"2025","journal-title":"JMIR Med Inform"},{"key":"B7","doi-asserted-by":"publisher","first-page":"898","DOI":"10.1038\/s41597-026-07261-9","article-title":"A dataset for evaluating large language models on Chinese National Medical Licensing Examinations.","volume":"13","author":"Zong","year":"2026","journal-title":"Sci Data."},{"key":"B8","doi-asserted-by":"publisher","first-page":"376","DOI":"10.1186\/s12909-024-06522-8","article-title":"Assessing training needs of primary care pharmacists: a cross-sectional survey in China.","volume":"25","author":"Sun","year":"2025","journal-title":"BMC Med Educ"},{"key":"B9","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1007\/s10916-025-02213-z","article-title":"Performance of DeepSeek-R1 and ChatGPT-4o on the Chinese National Medical Licensing Examination: a comparative study.","volume":"49","author":"Wu","year":"2025","journal-title":"J Med Syst"},{"key":"B10","doi-asserted-by":"publisher","first-page":"332","DOI":"10.1111\/eje.13073","article-title":"Evaluating the performance of large language models (LLMs) in answering and analysing the Chinese Dental Licensing Examination.","volume":"29","author":"Xiong","year":"2025","journal-title":"Eur J Dent Educ"},{"key":"B11","doi-asserted-by":"publisher","first-page":"113","DOI":"10.3390\/bioengineering13010113","article-title":"Large language models evaluation of medical licensing examination using GPT-4.0, ERNIE Bot 4.0, and GPT-4o.","volume":"13","author":"Lian","year":"2026","journal-title":"Bioengineering (Basel)"},{"key":"B12","doi-asserted-by":"publisher","first-page":"e69929","DOI":"10.2196\/69929","article-title":"Performance of ChatGPT-4o and four open-source large language models in generating diagnoses based on China\u2019s rare disease catalog: comparative study.","volume":"27","author":"Zhong","year":"2025","journal-title":"J Med Internet Res"},{"key":"B13","doi-asserted-by":"publisher","first-page":"517","DOI":"10.1016\/j.tics.2024.01.011","article-title":"Dissociating language and thought in large language models.","volume":"28","author":"Mahowald","year":"2024","journal-title":"Trends Cogn Sci"},{"key":"B14","doi-asserted-by":"publisher","first-page":"e57451","DOI":"10.2196\/57451","article-title":"Performance of GPT-3.5 and GPT-4 on the Korean Pharmacist Licensing Examination: comparison study.","volume":"10","author":"Jin","year":"2024","journal-title":"JMIR Med Educ"},{"key":"B15","doi-asserted-by":"publisher","first-page":"42096","DOI":"10.1038\/s41598-025-26036-7","article-title":"The pitfalls of multiple-choice questions in generative AI and medical education.","volume":"15","author":"Singh","year":"2025","journal-title":"Sci Rep"},{"key":"B16","doi-asserted-by":"publisher","first-page":"109441","DOI":"10.1016\/j.identj.2026.109441","article-title":"Performance of enhanced large language models on prosthodontic multiple-choice questions.","volume":"76","author":"Gao","year":"2026","journal-title":"Int Dent J"},{"key":"B17","doi-asserted-by":"publisher","first-page":"e81399","DOI":"10.2196\/81399","article-title":"Performance evaluation of large language models in multilingual medical multiple-choice questions: mixed methods study.","volume":"12","author":"Strasser","year":"2026","journal-title":"JMIR Med Educ"},{"key":"B18","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1038\/s41746-026-02619-0","article-title":"The effect of medical explanations from large language models on diagnostic accuracy in radiology.","volume":"9","author":"Spitzer","year":"2026","journal-title":"NPJ Digit Med"},{"key":"B19","doi-asserted-by":"publisher","first-page":"633","DOI":"10.1038\/s41586-025-09422-z","article-title":"DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning.","volume":"645","author":"Guo","year":"2025","journal-title":"Nature"},{"key":"B20","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1038\/s41591-024-03328-5","article-title":"An evaluation framework for clinical use of large language models in patient interaction tasks.","volume":"31","author":"Johri","year":"2025","journal-title":"Nat Med"},{"key":"B21","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1007\/s40265-024-02124-2","article-title":"Aligning large language models with humans: a comprehensive survey of ChatGPT\u2019s aptitude in pharmacology.","volume":"85","author":"Zhang","year":"2025","journal-title":"Drugs"},{"key":"B22","doi-asserted-by":"publisher","first-page":"3477","DOI":"10.1021\/acs.jmedchem.5c03511","article-title":"Benchmarking large language models for drug combination alerts: achieving expert-level reliability via knowledge grounding and contextual reasoning.","volume":"69","author":"Hu","year":"2026","journal-title":"J Med Chem"},{"key":"B23","doi-asserted-by":"publisher","first-page":"106527","DOI":"10.1016\/j.jinf.2025.106527","article-title":"Large language models (LLMs) in tuberculosis patients\u2019 health consultation and patient education: a comprehensive performance analysis study.","volume":"91","author":"Zhao","year":"2025","journal-title":"J Infect"},{"key":"B24","doi-asserted-by":"publisher","first-page":"101579","DOI":"10.1016\/j.jhepr.2025.101579","article-title":"Evaluating large language models\u2019 performance in answering common questions on drug-induced liver injury.","volume":"7","author":"Dong","year":"2025","journal-title":"JHEP Rep"},{"key":"B25","doi-asserted-by":"publisher","first-page":"569","DOI":"10.1038\/d41586-024-01641-0","article-title":"\u2018Fighting fire with fire\u2019 - using LLMs to combat LLM hallucinations.","volume":"630","author":"Verspoor","year":"2024","journal-title":"Nature"},{"key":"B26","doi-asserted-by":"publisher","first-page":"1083","DOI":"10.1080\/17425255.2025.2551724","article-title":"Language models for drug-drug interactions: current applications, pitfalls, and future directions.","volume":"21","author":"Al Meslamani","year":"2025","journal-title":"Expert Opin Drug Metab Toxicol"},{"key":"B27","doi-asserted-by":"publisher","first-page":"e68697","DOI":"10.2196\/68697","article-title":"AI\u2019s accuracy in extracting learning experiences from clinical practice logs: observational study.","volume":"11","author":"Kondo","year":"2025","journal-title":"JMIR Med Educ"},{"key":"B28","doi-asserted-by":"publisher","first-page":"101462","DOI":"10.1016\/j.ajpe.2025.101462","article-title":"Exploring the role of LLMs like ChatGPT in pharmacy education for supporting students\u2019 therapeutic decision-making.","volume":"89","author":"Carou-Senra","year":"2025","journal-title":"Am J Pharm Educ"},{"key":"B29","doi-asserted-by":"publisher","first-page":"e76925","DOI":"10.2196\/76925","article-title":"Performance evaluation of 18 generative AI models (ChatGPT, Gemini, Claude, and Perplexity) in 2024 Japanese Pharmacist Licensing Examination: comparative study.","volume":"11","author":"Sato","year":"2025","journal-title":"JMIR Med Educ"},{"key":"B30","doi-asserted-by":"publisher","first-page":"1500","DOI":"10.1186\/s12913-024-11815-1","article-title":"Perception, concerns, and practice of ChatGPT among Egyptian pharmacists: a cross-sectional study in Egypt.","volume":"24","author":"Taha","year":"2024","journal-title":"BMC Health Serv Res"},{"key":"B31","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1007\/s13755-025-00420-z","article-title":"Retrieval augmented large language model system for comprehensive drug contraindications.","volume":"14","author":"Bang","year":"2026","journal-title":"Health Inf Sci Syst"},{"key":"B32","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1007\/s40264-025-01594-x","article-title":"Leveraging large language models in extracting drug safety information from prescription drug labels.","volume":"49","author":"Gisladottir","year":"2026","journal-title":"Drug Saf."},{"key":"B33","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1038\/s41746-025-02277-8","article-title":"A novel evaluation benchmark for medical LLMs illuminating safety and effectiveness in clinical domains.","volume":"9","author":"Wang","year":"2025","journal-title":"NPJ Digit Med"},{"key":"B34","doi-asserted-by":"publisher","first-page":"e54601","DOI":"10.2196\/54601","article-title":"Using large language models to detect and understand drug discontinuation events in web-based forums: development and validation study.","volume":"27","author":"Trevena","year":"2025","journal-title":"J Med Internet Res"},{"key":"B35","doi-asserted-by":"publisher","first-page":"61048","DOI":"10.1021\/acsomega.5c04997","article-title":"Systematic review of drug-related interactions\u2014utilizing deep learning and LLMs for prediction and mitigation.","volume":"10","author":"Behrooznia","year":"2025","journal-title":"ACS Omega"},{"key":"B36","doi-asserted-by":"publisher","first-page":"5490","DOI":"10.3390\/jcm14155490","article-title":"Large language models for adverse drug events: a clinical perspective.","volume":"14","author":"Zitu","year":"2025","journal-title":"J Clin Med"},{"key":"B37","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1038\/s41746-025-01565-7","article-title":"A scoping review on generative AI and large language models in mitigating medication related harm.","volume":"8","author":"Ong","year":"2025","journal-title":"NPJ Digit Med"},{"key":"B38","doi-asserted-by":"publisher","first-page":"e2428276","DOI":"10.1001\/jamanetworkopen.2024.28276","article-title":"Enhancing postmarketing surveillance of medical products with large language models.","volume":"7","author":"Matheny","year":"2024","journal-title":"JAMA Netw Open"},{"key":"B39","doi-asserted-by":"publisher","first-page":"111135","DOI":"10.1016\/j.compbiomed.2025.111135","article-title":"Enhanced LLM-supported instructions for medication use through retrieval-augmented generation.","volume":"198","author":"de Jesus","year":"2025","journal-title":"Comput Biol Med"},{"key":"B40","doi-asserted-by":"publisher","first-page":"113128","DOI":"10.1016\/j.drugalcdep.2026.113128","article-title":"Foodie traps within Facebook cannabis promotional posts: deploying multimodal deep learning AIs to monitor audience engagement.","volume":"283","author":"Lu","year":"2026","journal-title":"Drug Alcohol Depend"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1880914\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T13:36:27Z","timestamp":1783344987000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1880914\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,6]]},"references-count":40,"alternative-id":["10.3389\/fmed.2026.1880914"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1880914","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,6]]},"article-number":"1880914"}}