[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-297085-105":59,"doc-detail-297085-en":131},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","ai-chatbots-show-promise-but-limitations-on-uk-medical-exam-questions-a-comparative-performance-study","AI chatbots show promise but limitations on UK medical exam questions: a comparative performance study","","The study evaluates how well publicly accessible large language models perform on simulated UK medical board exam questions. A total of 423 board-style items from nine UK exams were answered by seven LLMs, including ChatGPT-3.5, ChatGPT-4, Bard, Perplexity, Claude, Bing, and Claude Instant. Accuracy was graded across multiple-choice, true/false, and choose-N formats, with leaked questions excluded from primary analysis. Results show significant differences among models, with ChatGPT 4.0 highest and Perplexity lowest. All models performed better on multiple-choice than on other formats, revealing limitations requiring refinement before reliance in medical education.",{"@graph":69,"@context":123},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/ai-chatbots-show-promise-but-limitations-on-uk-medical-exam-questions-a-comparative-performance-study/297085/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/ai-chatbots-show-promise-but-limitations-on-uk-medical-exam-questions-a-comparative-performance-study/297085.png","ImageObject",300,407,{"name":92,"@type":93},"Lute","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-27","2026-09-18",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",12,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"Which large language models were evaluated for the UK medical board questions?","Question",{"text":113,"@type":114},"Seven publicly accessible LLMs were compared: ChatGPT-3.5, ChatGPT-4, Bard, Perplexity, Claude, Bing, and Claude Instant.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How many exam-style questions were used and what types were included?",{"text":118,"@type":114},"The study used 423 board-style questions from nine UK exams, including 406 multiple-choice, 13 true/false, and 4 choose-N questions.",{"name":120,"@type":111,"acceptedAnswer":121},"What were the main performance findings across the models and question formats?",{"text":122,"@type":114},"Significant differences appeared overall and in pairwise comparisons. All LLMs scored higher on multiple-choice questions than on true/false or choose-N items.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},297085,1790506833,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":145,"read_time":146,"preview_page_count":4},137454149569,"https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0","[www. nature.com/scientificreports](www. nature.com/scientificreports)  \nOPEN  \nAI chatbots show promise but limitations on UK medical exam questions: a comparative performance study  \nMohammed Ahmed Sadeq1,2,13*, Reem Mohamed Farouk Ghorab1,2,13, Mohamed HadyAshry2,3, Ahmed Mohamed Abozaid2,4, HaneenA. Banihani2,5, Moustafa Salem2,6, Mohammed Tawfiq Abu Aisheh2,7, Saad Abuzahra2,7, Marina Ramzy Mourid2,8, Mohamad MonifAssker2,9, Mohammed Ayyad2,10 & Mostafa Hossam El Din Moawad2,11,12  \nLarge language models (LLMs) like ChatGPT have potential applications in medical education such as helping students study for their licensing exams by discussing unclear questions with them. However, they require evaluation on these complex tasks. The purpose of this study was to evaluate how well publicly accessible LLMs performed on simulated UK medical board exam questions. 423 boardstyle questions from 9 UK exams (MRCS, MRCP, etc.) were answered by seven LLMs (ChatGPT-3.5, ChatGPT-4, Bard, Perplexity, Claude, Bing, Claude Instant). There were 406 multiple-choice, 13 true/ false, and 4 \"choose N\" questions covering topics in surgery, pediatrics, and other disciplines. The accuracy of the output was graded. Statistics were used to analyze differences among LLMs. Leaked questions were excluded from the primary analysis. ChatGPT 4.0 scored (78.2%), Bing (67.2%), Claude (64.4%), and Claude Instant (62.9%). Perplexity scored the lowest (56.1%) . Scores differed significantly between LLMs overall (p \u003C 0.001) and in pairwise comparisons. All LLMs scored higher on multiplechoice vs true/false or “choose N” questions. LLMs demonstrated limitations in answering certain questions, indicating refinements needed before primary reliance in medical education. However, their expanding capabilities suggest a potential to improve training if thoughtfully implemented. Further research should explore specialty specific LLMs and optimal integration into medical curricula.  \nArtificial intelligence (AI) is a multidisciplinary field focused on developing machines and programs capable of replicating intelligent behavior1. Such machines are intended to perform tasks that require human intelligence. These tasks may vary depending on the industry; however, they usually revolve around the ability to learn, rationalize, and comprehend abstract concepts1.  \nAI was first established as a scientific discipline at the Dartmouth Summer Research Project in 19552. However, over the past decade, the study of AI has experienced exponential growth and advances3. This was observed in different industries that integrated AI into their scope of work3. Despite the huge impact of these technologies in various industries, their application in medical field remains limited3.  \nIn November 2022, a new AI model called ChatGPT was launched by OpenAI. ChatGPT, also known as Chat Generative Pre-trained Transformer, is a Large language model (LLM) with a trained parameter count of 175 billion4. This AI model gained significant attention because of its remarkable capability to carry out complex  \n1Misr University for Science and Technology, 6th of October, Egypt. 2Medical Research Platform (MRP), Giza, Egypt. 3School of Medicine, New Giza University (NGU), Giza, Egypt. 4Faculty of Medicine, Tanta University, Tanta, Egypt. 5Faculty of Medicine, University of Jordan, Amman, Jordan. 6Faculty of Medicine, Mansoura University, Mansoura, Egypt. 7Department of Medicine, College of Medicine and Health Sciences, An-Najah National University, Nablus 44839, Palestine. 8Faculty of Medicine, Alexandria University, Alexandria, Egypt. 9Sheikh Khalifa Medical City, Abu Dhabi, UAE. 10Faculty of Medicine, Al-Quds University, Jerusalem, Palestine. 11Faculty of Pharmacy Clinical Department, Alexandria University, Alexandria, Egypt. 12Faculty of Medicine, Suez Canal University, Ismailia, Egypt. 13Emergency Medicine Department, Elsheikh Zayed Specialized Hospital, Elsheikh  \nZayed City, Egypt.*[email: mhd.a.sadeq@","cbCaihv5CwRPH1gB","https://ap.wps.com/l/cbCaihv5CwRPH1gB","pdf",1227236,11,"English","# Background and purpose\n## Simulated UK medical board exam evaluation\n# Methods and question set\n## Models compared and question types\n## Scoring and statistical analysis\n# Results\n## Accuracy across models and question formats\n# Discussion and implications\n## Limitations and future research","[{\"question\":\"Which large language models were evaluated for the UK medical board questions?\",\"answer\":\"Seven publicly accessible LLMs were compared: ChatGPT-3.5, ChatGPT-4, Bard, Perplexity, Claude, Bing, and Claude Instant.\"},{\"question\":\"How many exam-style questions were used and what types were included?\",\"answer\":\"The study used 423 board-style questions from nine UK exams, including 406 multiple-choice, 13 true/false, and 4 choose-N questions.\"},{\"question\":\"What were the main performance findings across the models and question formats?\",\"answer\":\"Significant differences appeared overall and in pairwise comparisons. All LLMs scored higher on multiple-choice questions than on true/false or choose-N items.\"}]","AI chatbots show promise but limitations on UK medical exam questions: a comparative performance study | PDF",1789740427,28]