{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T20:28:02Z","timestamp":1786998482714,"version":"build-2736575974"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,8,17]]},"DOI":"10.7759\/cureus.114680","type":"journal-article","created":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T19:28:11Z","timestamp":1786994891000},"source":"Crossref","is-referenced-by-count":0,"title":["Comparative Error Analysis of GPT-5.2 Reasoning Modes on Performance in Postgraduate Internal Medicine Single-Best-Answer Questions"],"prefix":"10.7759","author":[{"given":"Hiruna K","family":"Diyasena","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aadam","family":"Ahmad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thenuk H","family":"Weerasinghe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Olivia V","family":"Crawshaw","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anna A","family":"O'Brien","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1111\/medu.15402","article-title":"A systematic review of large language models and their implications in medical education","volume":"58","author":"Lucas HC","year":"2024","unstructured":"Lucas HC, Upperman JS, Robinson JR. A systematic review of large language models and their implications in medical education. Med Educ. 2024, 58:1276-85. 10.1111\/medu.15402","journal-title":"Med Educ"},{"key":"ref2","unstructured":"OpenAI Developers. Reasoning models. (2026). Accessed: February 16, 2026: https:\/\/platform.openai.com\/docs\/guides\/reasoning."},{"key":"ref3","unstructured":"MRCP (UK) Examinations. (2026). Accessed. February 16, 2026: https:\/\/www.mrcpuk.org\/mrcpuk-examinations."},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2023-080558","article-title":"Can ChatGPT pass the MRCP (UK) written examinations? Analysis of performance and errors using a clinical decision-reasoning framework","volume":"14","author":"Maitland A","year":"2024","unstructured":"Maitland A, Fowkes R, Maitland S. Can ChatGPT pass the MRCP (UK) written examinations? Analysis of performance and errors using a clinical decision-reasoning framework. BMJ Open. 2024, 14:e080558. 10.1136\/bmjopen-2023-080558","journal-title":"BMJ Open"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0307372","article-title":"Evaluating the competency of ChatGPT in MRCP Part 1 and a systematic literature review of its capabilities in postgraduate medical assessments","volume":"19","author":"Vij O","year":"2024","unstructured":"Vij O, Calver H, Myall N, Dey M, Kouranloo K. Evaluating the competency of ChatGPT in MRCP Part 1 and a systematic literature review of its capabilities in postgraduate medical assessments. PLoS One. 2024, 19:e0307372. 10.1371\/journal.pone.0307372","journal-title":"PLoS One"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2201.11903","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei J","year":"2022","unstructured":"Wei J, Wang X, Schuurmans D, et al.. Chain-of-thought prompting elicits reasoning in large language models. Adv Neural Inf Process Syst. 2022, 35:24824-37. 10.48550\/arXiv.2201.11903","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.240320","article-title":"Optimal large language model characteristics to balance accuracy and energy use for sustainable medical applications","volume":"312","author":"Doo FX","year":"2024","unstructured":"Doo FX, Savani D, Kanhere A, Carlos RC, Joshi A, Yi PH, Parekh VS. Optimal large language model characteristics to balance accuracy and energy use for sustainable medical applications. Radiology. 2024, 312:e240320. 10.1148\/radiol.240320","journal-title":"Radiology"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3390\/ejihpe14030043","article-title":"ChatGPT's response consistency: a study on repeated queries of medical examination questions","volume":"14","author":"Funk PF","year":"2024","unstructured":"Funk PF, Hoch CC, Knoedler S, et al.. ChatGPT's response consistency: a study on repeated queries of medical examination questions. Eur J Investig Health Psychol Educ. 2024, 14:657-68. 10.3390\/ejihpe14030043","journal-title":"Eur J Investig Health Psychol Educ"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-016-0377-1","article-title":"Cognitive biases associated with medical decisions: a systematic review","volume":"16","author":"Saposnik G","year":"2016","unstructured":"Saposnik G, Redelmeier D, Ruff CC, Tobler PN. Cognitive biases associated with medical decisions: a systematic review. BMC Med Inform Decis Mak. 2016, 16:138. 10.1186\/s12911-016-0377-1","journal-title":"BMC Med Inform Decis Mak"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1101\/2025.02.28.25323115","article-title":"Medical hallucination in foundation models and their impact on healthcare [PREPRINT]","author":"Kim Y","year":"2025","unstructured":"Kim Y, Jeong H, Chen S, et al.. Medical hallucination in foundation models and their impact on healthcare [PREPRINT]. medRxiv. 2025, 10.1101\/2025.02.28.25323115","journal-title":"medRxiv"},{"key":"ref11","unstructured":"The Federation of the Royal Colleges of Physicians of the UK. Part 1 sample questions. (2026). Accessed: February 16, 2026: https:\/\/www.thefederation.uk\/examinations\/part-1\/part-1-sample-questions."},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.landig.2025.100931","article-title":"Reasoning-driven large language models in medicine: opportunities, challenges, and the road ahead","volume":"8","author":"Wang X","year":"2026","unstructured":"Wang X, Xiong Z, Zou K, et al.. Reasoning-driven large language models in medicine: opportunities, challenges, and the road ahead. Lancet Digit Health. 2026, 8:100931. 10.1016\/j.landig.2025.100931","journal-title":"Lancet Digit Health"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocae131","article-title":"Reasoning with large language models for medical question answering","volume":"31","author":"Lucas MM","year":"2024","unstructured":"Lucas MM, Yang J, Pomeroy JK, Yang CC. Reasoning with large language models for medical question answering. J Am Med Inform Assoc. 2024, 31:1964-75. 10.1093\/jamia\/ocae131","journal-title":"J Am Med Inform Assoc"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2024.100943","article-title":"Can large language models reason about medical questions?","volume":"5","author":"Li\u00e9vin V","year":"2024","unstructured":"Li\u00e9vin V, Hother CE, Motzfeldt AG, Winther O. Can large language models reason about medical questions?. Patterns (N Y). 2024, 5:100943. 10.1016\/j.patter.2024.100943","journal-title":"Patterns (N Y)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2025.110614","article-title":"A comparative evaluation of chain-of-thought-based prompt engineering techniques for medical question answering","volume":"196","author":"Jeon S","year":"2025","unstructured":"Jeon S, Kim HG. A comparative evaluation of chain-of-thought-based prompt engineering techniques for medical question answering. Comput Biol Med. 2025, 196:110614. 10.1016\/j.compbiomed.2025.110614","journal-title":"Comput Biol Med"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.101","article-title":"What makes chain-of-thought prompting effective? A counterfactual study","author":"Madaan A","year":"2023","unstructured":"Madaan A, Hermann K, Yazdanbakhsh A. What makes chain-of-thought prompting effective? A counterfactual study. Findings of the Association for Computational Linguistics: EMNLP. 2023, 1448-535. 10.18653\/v1\/2023.findings-emnlp.101","journal-title":"Findings of the Association for Computational Linguistics: EMNLP"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-024-01283-6","article-title":"Evaluation and mitigation of cognitive biases in medical language models","volume":"7","author":"Schmidgall S","year":"2024","unstructured":"Schmidgall S, Harris C, Essien I, et al.. Evaluation and mitigation of cognitive biases in medical language models. NPJ Digit Med. 2024, 7:295. 10.1038\/s41746-024-01283-6","journal-title":"NPJ Digit Med"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1056\/AIcs2400639","article-title":"Cognitive biases and artificial intelligence","volume":"1","author":"Wang J","year":"2024","unstructured":"Wang J, Redelmeier DA. Cognitive biases and artificial intelligence. NEJM AI. 2024, 1:12. 10.1056\/AIcs2400639","journal-title":"NEJM AI"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1177\/0272989X251346788","article-title":"Forewarning artificial intelligence about cognitive biases","volume":"45","author":"Wang J","year":"2025","unstructured":"Wang J, Redelmeier DA. Forewarning artificial intelligence about cognitive biases. Med Decis Making. 2025, 45:913-6. 10.1177\/0272989X251346788","journal-title":"Med Decis Making"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.2214\/AJR.25.33955","article-title":"GPT-5, Gemini 2.5 Pro, and Qwen3 for answering clinical questions regarding ACR RADS guidelines","volume":"226","author":"Proff A","year":"2026","unstructured":"Proff A, Sieber J, Bahaaeldin M, et al.. GPT-5, Gemini 2.5 Pro, and Qwen3 for answering clinical questions regarding ACR RADS guidelines. AJR Am J Roentgenol. 2026, 226:e2533955. 10.2214\/AJR.25.33955","journal-title":"AJR Am J Roentgenol"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3390\/jcm15041512","article-title":"Is artificial intelligence ready for emergency department triage? A retrospective evaluation of multiple large language models in 39,375 patients at a university emergency department","volume":"15","author":"Nedos I","year":"2026","unstructured":"Nedos I, Zagalioti SC, Kofos C, et al.. Is artificial intelligence ready for emergency department triage? A retrospective evaluation of multiple large language models in 39,375 patients at a university emergency department. J Clin Med. 2026, 15:1512. 10.3390\/jcm15041512","journal-title":"J Clin Med"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1186\/s40981-026-00858-4","article-title":"Evaluation of the reliability of large language models for ASA-PS classification in cardiovascular surgery: a pilot study","volume":"12","author":"Iwabu K","year":"2026","unstructured":"Iwabu K, Juri T, Tsujikawa S, Hino H, Funai Y, Suehiro K, Mori T. Evaluation of the reliability of large language models for ASA-PS classification in cardiovascular surgery: a pilot study. JA Clin Rep. 2026, 12:24. 10.1186\/s40981-026-00858-4","journal-title":"JA Clin Rep"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.2196\/88053","article-title":"Increasing large language model accuracy for care-seeking advice using prompts reflecting human reasoning strategies in the real world: validation study","volume":"11","author":"Kopka M","year":"2026","unstructured":"Kopka M, Feufel MA. Increasing large language model accuracy for care-seeking advice using prompts reflecting human reasoning strategies in the real world: validation study. JMIR Biomed Eng. 2026, 11:e88053. 10.2196\/88053","journal-title":"JMIR Biomed Eng"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3389\/fcell.2026.1744389","article-title":"Comparative performance of GPT-4, GPT-o3, GPT-5, Gemini-3-Flash, and DeepSeek-R1 in ophthalmology question answering","volume":"14","author":"Zhang P","year":"2026","unstructured":"Zhang P, Wang J, Hu X, Wang X, Fan X, Chi W, Yang W. Comparative performance of GPT-4, GPT-o3, GPT-5, Gemini-3-Flash, and DeepSeek-R1 in ophthalmology question answering. Front Cell Dev Biol. 2026, 14:1744389. 10.3389\/fcell.2026.1744389","journal-title":"Front Cell Dev Biol"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.93479","article-title":"Assessment of the ability of the ChatGPT-5 model to pass the endocrinology specialization exam","volume":"17","author":"Latkowska A","year":"2025","unstructured":"Latkowska A, Sawina P, Dolata T, et al.. Assessment of the ability of the ChatGPT-5 model to pass the endocrinology specialization exam. Cureus. 2025, 17:e93479. 10.7759\/cureus.93479","journal-title":"Cureus"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1177\/00031348251390958","article-title":"Advances in large language model performance: a comparative study of ChatGPT-4 and ChatGPT-5 on ABSITE questions","author":"Sanli AN","year":"2025","unstructured":"Sanli AN, Turan B, Tekcan Sanli DE. Advances in large language model performance: a comparative study of ChatGPT-4 and ChatGPT-5 on ABSITE questions. Am Surg. 2025, 31348251390958. 10.1177\/00031348251390958","journal-title":"Am Surg"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-31251-3","article-title":"Comparative performance of ChatGPT-4o, ChatGPT-5, and gemini 2.5 flash on Persian internal medicine subspecialty board exams","volume":"16","author":"Sheikhalishahi S","year":"2025","unstructured":"Sheikhalishahi S, Haddadi A, Sadeghipour S, Rafiei F, Soltani H. Comparative performance of ChatGPT-4o, ChatGPT-5, and gemini 2.5 flash on Persian internal medicine subspecialty board exams. Sci Rep. 2025, 16:1371. 10.1038\/s41598-025-31251-3","journal-title":"Sci Rep"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.xops.2025.101034","article-title":"Performance of GPT-5 frontier models in ophthalmology question answering","volume":"6","author":"Antaki F","year":"2026","unstructured":"Antaki F, Mikhail D, Milad D, et al.. Performance of GPT-5 frontier models in ophthalmology question answering. Ophthalmol Sci. 2026, 6:101034. 10.1016\/j.xops.2025.101034","journal-title":"Ophthalmol Sci"},{"key":"ref29","doi-asserted-by":"publisher","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 S","year":"2025","unstructured":"Singh S, Alyakin A, Alber DA, et al.. The pitfalls of multiple-choice questions in generative AI and medical education. Sci Rep. 2025, 15:42096. 10.1038\/s41598-025-26036-7","journal-title":"Sci Rep"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.2196\/84120","article-title":"Knowledge-practice performance gap in clinical large language models: systematic review of 39 benchmarks","volume":"27","author":"Gong EJ","year":"2025","unstructured":"Gong EJ, Bang CS, Lee JJ, Baik GH. Knowledge-practice performance gap in clinical large language models: systematic review of 39 benchmarks. J Med Internet Res. 2025, 27:e84120. 10.2196\/84120","journal-title":"J Med Internet Res"}],"container-title":["Cureus"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.cureus.com\/articles\/516634-comparative-error-analysis-of-gpt-52-reasoning-modes-on-performance-in-postgraduate-internal-medicine-single-best-answer-questions","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T19:28:12Z","timestamp":1786994892000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.cureus.com\/articles\/516634-comparative-error-analysis-of-gpt-52-reasoning-modes-on-performance-in-postgraduate-internal-medicine-single-best-answer-questions"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,17]]},"references-count":30,"URL":"https:\/\/doi.org\/10.7759\/cureus.114680","relation":{},"ISSN":["2168-8184"],"issn-type":[{"value":"2168-8184","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8,17]]}}}