[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-369690-105":59,"doc-detail-369690-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","differential-performance-of-large-language-models-in-advanced-cardiac-life-support-assessment-a-comprehensive-multi-dimensional-analysis-of-accuracy-consistency-and-visual-recognition-capabilities","Differential performance of large language models in advanced cardiac life support assessment - A comprehensive multi-dimensional analysis of accuracy, consistency, and visual recognition capabilities","","Large Language Models (LLMs) are increasingly used in healthcare, but comparative evaluations in standardized medical assessments remain limited. This observational study tests the accuracy and consistency of four LLMs in answering Advanced Cardiac Life Support (ACLS) questions. Fifty questions are categorized as knowledge-based, visual content, and case-based, then posed to ChatGPT-4o, Gemini 2.0, Claude 3.5, and DeepSeek R1 across three separate occasions to measure response consistency. Three accuracy metrics evaluate overall, strict, and ideal correctness. Results show ChatGPT-4o achieves perfect accuracy and consistency, Claude 3.5 performs strongly with high consistency, while Gemini 2.0 and DeepSeek R1 show lower accuracy and reduced consistency, with DeepSeek R1 failing visual questions. Performance differences are statistically significant, emphasizing the need for critical evaluation before clinical use.",{"@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/differential-performance-of-large-language-models-in-advanced-cardiac-life-support-assessment-a-comprehensive-multi-dimensional-analysis-of-accuracy-consistency-and-visual-recognition-capabilities/369690/",{"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/differential-performance-of-large-language-models-in-advanced-cardiac-life-support-assessment-a-comprehensive-multi-dimensional-analysis-of-accuracy-consistency-and-visual-recognition-capabilities/369690.png","ImageObject",300,407,{"name":92,"@type":93},"Nguyễn Văn Học","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-19","2026-09-23",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",18,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"Which LLMs were evaluated for ACLS question answering?","Question",{"text":113,"@type":114},"ChatGPT-4o, Gemini 2.0, Claude 3.5, and DeepSeek R1 were assessed.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How were ACLS questions categorized and how was consistency measured?",{"text":118,"@type":114},"The study used 50 ACLS questions divided into knowledge-based, visual content, and case-based categories, and each question was answered by each model three separate times to assess consistency.",{"name":120,"@type":111,"acceptedAnswer":121},"What were the main accuracy and consistency findings across models?",{"text":122,"@type":114},"ChatGPT-4o showed 100% accuracy and perfect consistency, Claude 3.5 achieved high accuracy with excellent consistency, while Gemini 2.0 and DeepSeek R1 had lower accuracy and moderate consistency, with DeepSeek R1 failing visual content questions entirely.","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},369690,1790451271,{"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":19,"preview_urls":147},1374402739827,"https://ap-avatar.wpscdn.com/avatar/14000c97e7351f1a627?x-image-process=image/resize,m_fixed,w_180,h_180&k=1787885694763230660","OPEN ACCESS  \nCitation: Genc M, Bulut B, Akkan Öz M, Gür A, Yortanlı M, Yortanlı BÇ, et al. (2026) Differential performance of large language models in advanced cardiac life support assessment: A comprehensive multi-dimensional analysis of accuracy, consistency, and visual recognition capabilities. PLoS One 21(4): e0347611 .  \n[https://doi.org/10.1371/journal.pone.0347611](https://doi.org/10.1371/journal.pone.0347611)  \nEditor: Carla Pegoraro, PLOS, UNITED KINGDOM OF GREAT BRITAIN AND NORTHERN IRELAND  \nReceived: October 11, 2025  \nAccepted: April 2, 2026  \nPublished: April 29, 2026  \nCopyright: © 2026 Genc et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.  \nData availability statement: All relevant data are within the manuscript and its Supporting  information files.  \nRESEARCH ARTICLE  \nDifferential performance of large language models in advanced cardiac life support assessment: A comprehensive multi-dimensional analysis of accuracy, consistency, and visual recognition capabilities  \nMurat Genc1, Bensu Bulut2*, Medine Akkan Öz2, Ayşenur Gür3, Mehmet Yortanlı4, Betül Çiğdem Yortanlı5, Oguz Sariyildiz6, Ramiz Yazici7, Hüseyin Mutlu8,  \nZekeriya Uykan9  \n1 Department of Emergency Medicine, Ankara Training and Research Hospital, Ankara, Turkey,  \n2 Department of Emergency Medicine, Ankara Gulhane Training and Research Hospital, Health Science University, Ankara, Turkey, 3 Department of Emergency Medicine, Etimesgut Şehit Sait Ertürk State Hospital, Ankara, Turkey, 4 Department of Emergency Medicine, Konya Numune Hospital, Konya, Turkey, 5 Department of Internal Medicine, Konya City Hospital, University of Health Sciences, Konya, Turkey, 6 Department of Anesthesıology And Reanımatıon Department, 75th Year Oral And Dental Health Hospital, Ankara, Turkey, 7 Department of Emergency Medicine, Istanbul Kanuni Sultan Suleyman Training and Research Hospital, Health Science University, Istanbul, Turkey, 8 Department of Emergency Medicine, Aksaray Training and Research Hospital, Aksaray University, Aksaray, Turkey, 9 College of Engineering and Technology, American University of the Middle East, Egaila, Kuwait  \n* [bensu.bulut@gmail.com](bensu.bulut@gmail.com)  \nAbstract  \nBackground  \nLarge Language Models (LLMs) have been increasingly adopted in healthcare settings, yet comparative evaluations of their performance in standardized medical assessments remain limited. This study aims to evaluate the accuracy and consistency of four LLMs in answering Advanced Cardiac Life Support (ACLS) questions.  \nMethods  \nIn this observational study, 50 ACLS questions were categorized as knowledgebased (n = 29), visual content (n = 12), or case-based (n = 9) . Each question was posed to ChatGPT-4o, Gemini 2.0, Claude 3.5, and DeepSeek R1 on three separate occasions to assess consistency. Performance was evaluated using three accuracy metrics: overall accuracy (all three responses correct), strict accuracy (at least two responses correct), and ideal accuracy (at least one response correct) .  \nResults  \nChatGPT-4o demonstrated superior performance with 100% accuracy across all categories and perfect consistency (Fleiss’ Kappa = 1.0) . Claude 3.5 achieved 92.0% overall accuracy with excellent consistency (Fleiss’ Kappa = 0.89) . Gemini 2.0 showed  \nPLOS One | [https://doi.org/10.1371/journal.pone.0347611](https://doi.org/10.1371/journal.pone.0347611) April 29, 2026 1 / 13  \nFunding: The author(s) received no specific funding for this work.  \nCompeting interests: The authors have declared that no competing interests exist.  \n86.0% overall accuracy with moderate consistency (Fleiss’ Kappa = 0.58) . DeepSeek R1 performed lowest at 70.0% overall accuracy with moderate consistency (Fleiss’Kappa = 0.58) and failed completely on visual content questions (0%) . All models a","cbCaigY9WYEVuaqO","https://ap.wps.com/l/cbCaigY9WYEVuaqO","pdf",991443,13,"English","# Abstract\n## Background\n## Methods\n## Results\n## Conclusion\n# Introduction\n## Cardiovascular burden and ACLS importance\n## ACLS training and assessment","[{\"question\":\"Which LLMs were evaluated for ACLS question answering?\",\"answer\":\"ChatGPT-4o, Gemini 2.0, Claude 3.5, and DeepSeek R1 were assessed.\"},{\"question\":\"How were ACLS questions categorized and how was consistency measured?\",\"answer\":\"The study used 50 ACLS questions divided into knowledge-based, visual content, and case-based categories, and each question was answered by each model three separate times to assess consistency.\"},{\"question\":\"What were the main accuracy and consistency findings across models?\",\"answer\":\"ChatGPT-4o showed 100% accuracy and perfect consistency, Claude 3.5 achieved high accuracy with excellent consistency, while Gemini 2.0 and DeepSeek R1 had lower accuracy and moderate consistency, with DeepSeek R1 failing visual content questions entirely.\"}]","Differential performance of large language models in advanced cardiac life support assessment - A comprehensive multi-dimensional analysis of accuracy, consistency, and visual recognition capabilities | PDF",1790184110,33,[148,152,156,160],{"page_no":8,"url":149,"width":150,"height":151},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/bfe537e0b27376844367222c8f4ff2c8.webp",983,1272,{"page_no":14,"url":153,"width":154,"height":155},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/5bf52bcee888de44fabbbb28a087f20d.webp",982,1270,{"page_no":81,"url":157,"width":158,"height":159},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/eac6b9ba8259e12889cdeb32c6107bf1.webp",981,1269,{"page_no":19,"url":161,"width":162,"height":163},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/76d59793342cf7ecbf6eb4837e2c422c.webp",980,1268]