{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T02:52:47Z","timestamp":1777690367837,"version":"3.51.4"},"reference-count":39,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T00:00:00Z","timestamp":1757116800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","award":["101055874"],"award-info":[{"award-number":["101055874"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computers and Education: Artificial Intelligence"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1016\/j.caeai.2025.100475","type":"journal-article","created":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T16:35:23Z","timestamp":1757608523000},"page":"100475","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":2,"special_numbering":"C","title":["How do LLMs perform in the context of MCQs across different levels of thinking skills in a business education course at higher education? A comparison of ChatGPT, Gemini, and Copilot"],"prefix":"10.1016","volume":"9","author":[{"given":"Laurens","family":"Goorts","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0592-0662","authenticated-orcid":false,"given":"Ryan","family":"Hollevoet","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vanessa","family":"Xia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Felix","family":"Cammaerts","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3626-2101","authenticated-orcid":false,"given":"Almer","family":"G\u00fcng\u00f6r","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"issue":"6","key":"10.1016\/j.caeai.2025.100475_bib1","doi-asserted-by":"crossref","first-page":"1549","DOI":"10.1007\/s00259-023-06172-w","article-title":"Large language models (LLM) and ChatGPT: What will the impact on nuclear medicine be?","volume":"50","author":"Alberts","year":"2023","journal-title":"European Journal of Nuclear Medicine and Molecular Imaging"},{"key":"10.1016\/j.caeai.2025.100475_bib3","author":"Bates"},{"key":"10.1016\/j.caeai.2025.100475_bib4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v067.i01","article-title":"Fitting linear mixed-effects models using lme4","volume":"67","author":"Bates","year":"2015","journal-title":"Journal of Statistical Software"},{"issue":"5","key":"10.1016\/j.caeai.2025.100475_bib5","doi-asserted-by":"crossref","DOI":"10.1148\/radiol.230582","article-title":"Performance of ChatGPT on a radiology board-style examination: Insights into current strengths and limitations","volume":"307","author":"Bhayana","year":"2023","journal-title":"Radiology"},{"issue":"3","key":"10.1016\/j.caeai.2025.100475_bib6","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1007\/s40670-016-0275-2","article-title":"Theory, process, and validation evidence for a staff-driven medical education exam quality improvement process","volume":"26","author":"Bibler Zaidi","year":"2016","journal-title":"Medical Science Educator"},{"key":"10.1016\/j.caeai.2025.100475_bib7","series-title":"Taxonomy of educational objectives: The classification of educational goals","author":"Bloom","year":"1956"},{"issue":"3","key":"10.1016\/j.caeai.2025.100475_bib8","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1016\/j.tree.2008.10.008","article-title":"Generalized linear mixed models: A practical guide for ecology and evolution","volume":"24","author":"Bolker","year":"2009","journal-title":"Trends in Ecology & Evolution"},{"key":"10.1016\/j.caeai.2025.100475_bib9","article-title":"A categorical archive of ChatGPT failures","author":"Borji","year":"2023","journal-title":"arXiv.org"},{"key":"10.1016\/j.caeai.2025.100475_bib10","unstructured":"Brown, T., B.,M., Ryder, N., Subbiah, M., Kaplan, J., P.,D., \u2026 Ramesh, A. (2020). Language models are few-shot learners. Advances in neural information processing systems, 33, 1877-1901."},{"issue":"11","key":"10.1016\/j.caeai.2025.100475_bib11","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0112653","article-title":"Methodological quality and reporting of generalized linear mixed models in clinical medicine (2000\u20132012): A systematic review","volume":"9","author":"Casals","year":"2014","journal-title":"PLoS One"},{"key":"10.1016\/j.caeai.2025.100475_bib12","series-title":"When do you need chain-of-thought prompting for ChatGPT?","author":"Chen","year":"2023"},{"issue":"1","key":"10.1016\/j.caeai.2025.100475_bib13","doi-asserted-by":"crossref","first-page":"864","DOI":"10.1186\/s12909-023-04832-x","article-title":"Assessment of the capacity of ChatGPT as a self-learning tool in medical pharmacology: A study using MCQs","volume":"23","author":"Choi","year":"2023","journal-title":"BMC Medical Education"},{"key":"10.1016\/j.caeai.2025.100475_bib14","first-page":"81","article-title":"Natural language processing","author":"Chowdhury","year":"2003","journal-title":"Annual Review of Information Science & Technology"},{"key":"10.1016\/j.caeai.2025.100475_bib15","doi-asserted-by":"crossref","unstructured":"Cribben, I., & Yasser, Z. (2023). The benefits and limitations of ChatGPT in business education and research: A focus on management science, operations management and data analytics. SSRN Electronic Journal. Retrieved from: http:\/\/dx.doi.org\/10.2139\/ssrn.4404276.","DOI":"10.2139\/ssrn.4404276"},{"key":"10.1016\/j.caeai.2025.100475_bib17","doi-asserted-by":"crossref","unstructured":"Dos Santos, R.P. (2023). Enhancing physics learning with ChatGPT, Bing chat, and Bard as Agents-to-Think-With: A comparative case Study. SSRN Electronic Journal. Retrieved from:http:\/\/dx.doi.org\/10.2139\/ssrn.4478305.","DOI":"10.2139\/ssrn.4478305"},{"key":"10.1016\/j.caeai.2025.100475_bib16","author":"Di Nicola"},{"issue":"2","key":"10.1016\/j.caeai.2025.100475_bib18","doi-asserted-by":"crossref","DOI":"10.1177\/05694345231169654","article-title":"ChatGPT has aced the test of understanding in college economics: Now what?","volume":"68","author":"Geerling","year":"2023","journal-title":"The American Economist"},{"key":"10.1016\/j.caeai.2025.100475_bib19","doi-asserted-by":"crossref","DOI":"10.2196\/52113","article-title":"Assessing chatgpt's mastery of Bloom's taxonomy using psychosomatic medicine exam questions: Mixed-methods study","volume":"26","author":"Herrmann-Werner","year":"2024","journal-title":"Journal of Medical Internet Research"},{"issue":"3","key":"10.1016\/j.caeai.2025.100475_bib20","doi-asserted-by":"crossref","first-page":"198","DOI":"10.3390\/ime2030019","article-title":"Prompt engineering in medical education","volume":"2","author":"Heston","year":"2023","journal-title":"International Medical Education"},{"key":"10.1016\/j.caeai.2025.100475_bib21","doi-asserted-by":"crossref","first-page":"212","DOI":"10.1207\/s15430421tip4104_2","article-title":"A revision of bloom's taxonomy: An overview","author":"Krathwohl","year":"2002","journal-title":"Theory into practice"},{"key":"10.1016\/j.caeai.2025.100475_bib22","series-title":"Can language models learn from explanations in context? Findings of the Association for Computational Linguistics","author":"Lampinen","year":"2022"},{"key":"10.1016\/j.caeai.2025.100475_bib23","article-title":"Multiple-choice questions (MCQs) for higher-order cognition: Perspectives of university teachers","author":"Liu","year":"2023","journal-title":"Innovations in Education & Teaching International"},{"key":"10.1016\/j.caeai.2025.100475_bib24","doi-asserted-by":"crossref","first-page":"1328769","DOI":"10.3389\/feduc.2024.1328769","article-title":"The use of ChatGPT in teaching and learning: A systematic review through SWOT analysis approach","volume":"9","author":"Mai","year":"2024","journal-title":"Frontiers in Education"},{"issue":"4","key":"10.1016\/j.caeai.2025.100475_bib2","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1007\/s11165-006-9029-2","article-title":"Purposely teaching for the promotion of higher-order thinking skills: A case of critical thinking","volume":"37","author":"Miri","year":"2007","journal-title":"Research in Science Education"},{"key":"10.1016\/j.caeai.2025.100475_bib26","first-page":"277","article-title":"Generative AI and ChatGPT: Applications, challengens and AI-human collaboration","author":"Nah","year":"2023","journal-title":"Journal of Information Technology Case and Application Research"},{"issue":"1","key":"10.1016\/j.caeai.2025.100475_bib28","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1080\/03098770601167922","article-title":"E\u2010assessment by design: Using multiple\u2010choice tests to good effect","volume":"31","author":"Nicol","year":"2007","journal-title":"Journal of Further and Higher Education"},{"key":"10.1016\/j.caeai.2025.100475_bib29","series-title":"Cambridge NA report NA2009\/06","first-page":"26","article-title":"The BOBYQA algorithm for bound constrained optimization without derivatives","volume":"Vol. 26","author":"Powell","year":"2009"},{"key":"10.1016\/j.caeai.2025.100475_bib30","article-title":"Performance of ChatGPT on the US fundamentals of engineering exam: Comprehensive assessment of proficiency and potential implications for professional environmental engineering practice","volume":"5","author":"Pursnani","year":"2023","journal-title":"Computers and Education: Artificial Intelligence"},{"key":"10.1016\/j.caeai.2025.100475_bib31","series-title":"Leveraging large Language models for multiple choice question answering. International conference on learning representations","author":"Robinson","year":"2023"},{"key":"10.1016\/j.caeai.2025.100475_bib32","article-title":"Assessing the quality of automatic-generated short answers using GPT-4","volume":"7","author":"Rodrigues","year":"2024","journal-title":"Computers and Education: Artificial Intelligence"},{"key":"10.1016\/j.caeai.2025.100475_bib33","first-page":"1155","article-title":"The positive and negative consequences of multiple-choice testing","volume":"31","author":"Roediger","year":"2005","journal-title":"Journal of Experimental Psychology: Learning, Memory, & Cognition"},{"key":"10.1016\/j.caeai.2025.100475_bib34","series-title":"Proceedings of the 47th international ACM SIGIR conference on research and development in information retrieval","first-page":"2316","article-title":"Can LLMs master math? Investigating large Language models on math stack exchange","author":"Satpute","year":"2024"},{"key":"10.1016\/j.caeai.2025.100475_bib35","first-page":"7","volume":"medRxiv","author":"Schubert","year":"2023","journal-title":"Evaluating the performance of large language models on a neurology board-style examination"},{"issue":"1","key":"10.1016\/j.caeai.2025.100475_bib36","article-title":"Opportunities, challenges, and strategies for using ChatGPT in higher education: A literature review","volume":"4","author":"Sok","year":"2024","journal-title":"Ournal of Digital Educational Technology"},{"key":"10.1016\/j.caeai.2025.100475_bib37","series-title":"Quantitative methods in the humanities the humanities and social sciences","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-69830-4","article-title":"Mixed-Effects regression models in linguistics","author":"Speelman","year":"2018"},{"issue":"1","key":"10.1016\/j.caeai.2025.100475_bib38","doi-asserted-by":"crossref","first-page":"33","DOI":"10.33461\/uybisbbd.1244777","article-title":"The role of artificial intelligence in higher education: ChatGPT assessment for anatomy course","volume":"7","author":"Talan","year":"2023","journal-title":"Uluslararas\u0131 Y\u00f6netim Bili\u015fim Sistemleri Ve Bilgisayar Bilimleri Dergisi"},{"key":"10.1016\/j.caeai.2025.100475_bib39","series-title":"Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","first-page":"5037","article-title":"Robust (controlled) table-to-text generation with structure-aware equivariance learning","author":"Wang","year":"2022"},{"key":"10.1016\/j.caeai.2025.100475_bib41","article-title":"AGIEval: A human-centric benchmark for evaluating foundation models","author":"Zhong","year":"2023","journal-title":"arXiv. org."},{"key":"10.1016\/j.caeai.2025.100475_bib40","unstructured":"Zhang, Z., Jiang, Z., Xu, L., Hao, H., & Wang, R. (2024). Multiple-Choice questions are efficient and robust LLM evaluators. arXiv.org. https:\/\/doi.org\/10.48550\/arXiv.2405.11966."}],"container-title":["Computers and Education: Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2666920X25001158?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2666920X25001158?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T07:13:33Z","timestamp":1777274013000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2666920X25001158"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":39,"alternative-id":["S2666920X25001158"],"URL":"https:\/\/doi.org\/10.1016\/j.caeai.2025.100475","relation":{},"ISSN":["2666-920X"],"issn-type":[{"value":"2666-920X","type":"print"}],"subject":[],"published":{"date-parts":[[2025,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"How do LLMs perform in the context of MCQs across different levels of thinking skills in a business education course at higher education? A comparison of ChatGPT, Gemini, and Copilot","name":"articletitle","label":"Article Title"},{"value":"Computers and Education: Artificial Intelligence","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.caeai.2025.100475","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 The Authors. Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"100475"}}