{"id":"https://openalex.org/W7127449028","doi":"https://doi.org/10.1186/s12911-026-03370-y","title":"Textbook-level medical knowledge in large language models: comparative evaluation using Japanese National Medical Examination","display_name":"Textbook-level medical knowledge in large language models: comparative evaluation using Japanese National Medical Examination","publication_year":2026,"publication_date":"2026-02-03","ids":{"openalex":"https://openalex.org/W7127449028","doi":"https://doi.org/10.1186/s12911-026-03370-y","pmid":"https://pubmed.ncbi.nlm.nih.gov/41634738"},"language":"en","primary_location":{"id":"doi:10.1186/s12911-026-03370-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12911-026-03370-y","pdf_url":null,"source":{"id":"https://openalex.org/S107516304","display_name":"BMC Medical Informatics and Decision Making","issn_l":"1472-6947","issn":["1472-6947"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Medical Informatics and Decision Making","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1186/s12911-026-03370-y","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124935660","display_name":"Mingxin Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Mingxin Liu","raw_affiliation_strings":["Department of Health Communication, Graduate School of Medicine, The University of Tokyo, Hongo 7-3-1, Bunkyo, Tokyo, Japan. liumingxin98@g.ecc.u-tokyo.ac.jp"],"raw_orcid":"https://orcid.org/0000-0001-6320-544X","affiliations":[{"raw_affiliation_string":"Department of Health Communication, Graduate School of Medicine, The University of Tokyo, Hongo 7-3-1, Bunkyo, Tokyo, Japan. liumingxin98@g.ecc.u-tokyo.ac.jp","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067331393","display_name":"Tsuyoshi Okuhara","orcid":"https://orcid.org/0000-0002-6251-3587"},"institutions":[{"id":"https://openalex.org/I4210117013","display_name":"University of Tokyo Health Sciences","ror":"https://ror.org/02tefzr61","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210117013"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tsuyoshi Okuhara","raw_affiliation_strings":["Department of Health Communication, School of Public Health, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-6251-3587","affiliations":[{"raw_affiliation_string":"Department of Health Communication, School of Public Health, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I4210117013"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124906836","display_name":"Zhehao Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Zhehao Dai","raw_affiliation_strings":["Department of Cardiovascular Medicine, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-0363-7563","affiliations":[{"raw_affiliation_string":"Department of Cardiovascular Medicine, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108114143","display_name":"Ming Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]},{"id":"https://openalex.org/I4210096386","display_name":"Bridge University","ror":"https://ror.org/00cbm0437","country_code":"SS","type":"education","lineage":["https://openalex.org/I4210096386"]}],"countries":["GB","SS"],"is_corresponding":false,"raw_author_name":"Minghong Zhao","raw_affiliation_strings":["Department of engineering, University of Cambridge, Cambridge, UK"],"raw_orcid":"https://orcid.org/0009-0008-7910-1977","affiliations":[{"raw_affiliation_string":"Department of engineering, University of Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I241749","https://openalex.org/I4210096386"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124924064","display_name":"Wenqiang Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Wenqiang Yin","raw_affiliation_strings":["Faculty of Medicine, The University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Medicine, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124933261","display_name":"Hiroko Okada","orcid":null},"institutions":[{"id":"https://openalex.org/I4210117013","display_name":"University of Tokyo Health Sciences","ror":"https://ror.org/02tefzr61","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210117013"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroko Okada","raw_affiliation_strings":["Department of Health Communication, School of Public Health, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0001-7877-9753","affiliations":[{"raw_affiliation_string":"Department of Health Communication, School of Public Health, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I4210117013"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009722240","display_name":"Emi Furukawa","orcid":"https://orcid.org/0000-0002-1431-4786"},"institutions":[{"id":"https://openalex.org/I4210117013","display_name":"University of Tokyo Health Sciences","ror":"https://ror.org/02tefzr61","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210117013"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Emi Furukawa","raw_affiliation_strings":["Department of Health Communication, School of Public Health, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-1431-4786","affiliations":[{"raw_affiliation_string":"Department of Health Communication, School of Public Health, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I4210117013"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070326203","display_name":"Takahiro Kiuchi","orcid":"https://orcid.org/0000-0001-5934-0681"},"institutions":[{"id":"https://openalex.org/I4210117013","display_name":"University of Tokyo Health Sciences","ror":"https://ror.org/02tefzr61","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210117013"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takahiro Kiuchi","raw_affiliation_strings":["Department of Health Communication, School of Public Health, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0001-5934-0681","affiliations":[{"raw_affiliation_string":"Department of Health Communication, School of Public Health, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I4210117013"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5124935660"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":{"value":2690,"currency":"USD","value_usd":2690},"apc_paid":{"value":2690,"currency":"USD","value_usd":2690},"fwci":8.743,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.9651888,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"26","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.2944999933242798,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.2944999933242798,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10254","display_name":"Innovations in Medical Education","score":0.1632000058889389,"subfield":{"id":"https://openalex.org/subfields/2739","display_name":"Public Health, Environmental and Occupational Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12574","display_name":"Clinical Reasoning and Diagnostic Skills","score":0.08389999717473984,"subfield":{"id":"https://openalex.org/subfields/2714","display_name":"Family Practice"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/health-informatics","display_name":"Health informatics","score":0.5789999961853027},{"id":"https://openalex.org/keywords/confusion","display_name":"Confusion","score":0.5630999803543091},{"id":"https://openalex.org/keywords/unified-medical-language-system","display_name":"Unified Medical Language System","score":0.5332000255584717},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.5295000076293945},{"id":"https://openalex.org/keywords/medical-imaging","display_name":"Medical imaging","score":0.3668999969959259},{"id":"https://openalex.org/keywords/medline","display_name":"MEDLINE","score":0.34630000591278076}],"concepts":[{"id":"https://openalex.org/C145642194","wikidata":"https://www.wikidata.org/wiki/Q870895","display_name":"Health informatics","level":3,"score":0.5789999961853027},{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.5630999803543091},{"id":"https://openalex.org/C69505689","wikidata":"https://www.wikidata.org/wiki/Q455338","display_name":"Unified Medical Language System","level":2,"score":0.5332000255584717},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.5295000076293945},{"id":"https://openalex.org/C509550671","wikidata":"https://www.wikidata.org/wiki/Q126945","display_name":"Medical education","level":1,"score":0.47609999775886536},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.46219998598098755},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.3668999969959259},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.34630000591278076},{"id":"https://openalex.org/C2985722590","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medical knowledge","level":2,"score":0.3395000100135803},{"id":"https://openalex.org/C3020132585","wikidata":"https://www.wikidata.org/wiki/Q2671652","display_name":"Diagnostic accuracy","level":2,"score":0.3197999894618988},{"id":"https://openalex.org/C80059220","wikidata":"https://www.wikidata.org/wiki/Q7521302","display_name":"Simulated patient","level":2,"score":0.311599999666214},{"id":"https://openalex.org/C206179267","wikidata":"https://www.wikidata.org/wiki/Q188952","display_name":"Medical history","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.2953999936580658},{"id":"https://openalex.org/C22156102","wikidata":"https://www.wikidata.org/wiki/Q5341294","display_name":"Educational measurement","level":3,"score":0.2953000068664551},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2793999910354614},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2782999873161316},{"id":"https://openalex.org/C512399662","wikidata":"https://www.wikidata.org/wiki/Q3505712","display_name":"Family medicine","level":1,"score":0.25999999046325684},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.25929999351501465}],"mesh":[{"descriptor_ui":"D000095225","descriptor_name":"East Asian People","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004501","descriptor_name":"Education, Medical","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":true},{"descriptor_ui":"D004501","descriptor_name":"Education, Medical","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":true},{"descriptor_ui":"D004501","descriptor_name":"Education, Medical","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":true},{"descriptor_ui":"D004521","descriptor_name":"Educational Measurement","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":true},{"descriptor_ui":"D004521","descriptor_name":"Educational Measurement","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":true},{"descriptor_ui":"D004521","descriptor_name":"Educational Measurement","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007564","descriptor_name":"Japan","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007564","descriptor_name":"Japan","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007564","descriptor_name":"Japan","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008007","descriptor_name":"Licensure, Medical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008007","descriptor_name":"Licensure, Medical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008007","descriptor_name":"Licensure, Medical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1186/s12911-026-03370-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12911-026-03370-y","pdf_url":null,"source":{"id":"https://openalex.org/S107516304","display_name":"BMC Medical Informatics and Decision Making","issn_l":"1472-6947","issn":["1472-6947"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Medical Informatics and Decision Making","raw_type":"journal-article"},{"id":"pmid:41634738","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41634738","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC medical informatics and decision making","raw_type":null},{"id":"pmh:oai:doaj.org/article:2754752439664a28bea7d2d64c3f1cb1","is_oa":true,"landing_page_url":"https://doaj.org/article/2754752439664a28bea7d2d64c3f1cb1","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Medical Informatics and Decision Making, Vol 26, Iss 1 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s12911-026-03370-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12911-026-03370-y","pdf_url":null,"source":{"id":"https://openalex.org/S107516304","display_name":"BMC Medical Informatics and Decision Making","issn_l":"1472-6947","issn":["1472-6947"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Medical Informatics and Decision Making","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8830187320709229}],"awards":[{"id":"https://openalex.org/G1975109764","display_name":"Accuracy and reliability of health and medical information provided by artificial intelligence chatbot : An evaluation stuay","funder_award_id":"24KJ0830","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W4319460874","https://openalex.org/W4378229839","https://openalex.org/W4380685958","https://openalex.org/W4383749364","https://openalex.org/W4385230848","https://openalex.org/W4385430748","https://openalex.org/W4386023761","https://openalex.org/W4386439692","https://openalex.org/W4386616134","https://openalex.org/W4387028645","https://openalex.org/W4388500499","https://openalex.org/W4388822338","https://openalex.org/W4388896754","https://openalex.org/W4389235809","https://openalex.org/W4389379994","https://openalex.org/W4389795202","https://openalex.org/W4389803273","https://openalex.org/W4390167939","https://openalex.org/W4390268708","https://openalex.org/W4390617165","https://openalex.org/W4392702964","https://openalex.org/W4394674889","https://openalex.org/W4399701665","https://openalex.org/W4403827315","https://openalex.org/W4403869417","https://openalex.org/W4404288320","https://openalex.org/W4408251534","https://openalex.org/W4410280049","https://openalex.org/W4411004403","https://openalex.org/W4412367130","https://openalex.org/W4413801922"],"related_works":[],"abstract_inverted_index":{"BACKGROUND:":[0],"The":[1,317],"accuracy":[2,169,179,201,216],"of":[3,42,131,170,239,319],"the":[4,40,57,84,128,132,167,187,199,272,276,305],"latest":[5],"reasoning-enhanced":[6,44],"large":[7,45],"language":[8,46],"models":[9,47],"on":[10,183,217,224,275,284],"national":[11],"medical":[12,33,76,121,286,299],"licensing":[13],"examinations":[14],"remains":[15],"unknown,":[16],"which":[17],"is":[18],"crucial":[19],"for":[20,32,137,142,145,151,186,203,206,210,292],"determining":[21],"how":[22],"close":[23],"they":[24],"are":[25],"to":[26,38,126,247,339],"serving":[27],"as":[28,68,294],"effective":[29],"knowledge":[30,287],"sources":[31],"education.":[34,300],"This":[35],"study":[36],"aimed":[37],"evaluate":[39],"performance":[41,82,283,308],"four":[43,133],"(LLMs)\u2014GPT-5,":[48],"Grok-4,":[49,152],"Claude":[50,146],"Opus":[51,147],"4.1,":[52,148],"and":[53,71,86,106,119,149,160,172,208,252,278,331],"Gemini":[54,138,163,194,301],"2.5":[55,139,164,195,302],"Pro\u2014on":[56],"Japanese":[58],"National":[59],"Medical":[60],"Examination":[61],"(JNME),":[62],"providing":[63,231],"insights":[64],"into":[65,95],"their":[66,72,279,334],"potential":[67,291],"educational":[69],"resources":[70,296],"future":[73],"applicability":[74],"in":[75,235,254,258,269,297,321],"practice.":[77],"METHODS:":[78],"We":[79],"evaluated":[80],"LLM":[81],"using":[83],"2019":[85],"2025":[87,270],"JNME":[88],"(n":[89],"=":[90],"793).":[91],"Questions":[92],"were":[93,112,135],"entered":[94],"each":[96,214],"model":[97],"with":[98,153,174,261],"chain-of-thought":[99],"prompting":[100],"enabled.":[101],"Accuracy":[102],"was":[103,180,220],"assessed":[104],"overall":[105,129],"by":[107,115],"question":[108,310],"type.":[109],"Incorrect":[110],"responses":[111],"qualitatively":[113],"reviewed":[114],"a":[116,120],"licensed":[117],"physician":[118],"student.":[122],"RESULTS:":[123],"From":[124],"highest":[125,168,200],"lowest,":[127],"accuracies":[130],"LLMs":[134,267,326],"97.2%":[136],"Pro,":[140],"96.3%":[141],"GPT-5,":[143],"96.1%":[144,171],"95.6%":[150],"no":[154,175],"significant":[155,176],"pairwise":[156],"differences.":[157],"For":[158],"image-based":[159,184],"non-image-based":[161],"items,":[162],"Pro":[165,196,303],"achieved":[166,198],"97.6%,":[173],"difference,":[177],"whereas":[178],"significantly":[181,221],"lower":[182,222],"items":[185],"other":[188],"three":[189],"LLMs.":[190],"Across":[191],"difficulty":[192],"levels,":[193],"again":[197],"(98.4%":[202],"easy,":[204],"97.3%":[205],"moderate,":[207],"93.2%":[209],"difficult":[211,218],"items).":[212],"Within":[213],"LLM,":[215],"questions":[219,260,288,323],"than":[223],"easy":[225],"questions.":[226],"Common":[227],"error":[228],"patterns":[229],"included":[230],"unnecessary":[232],"additional":[233],"options":[234],"single-choice":[236],"questions,":[237],"misdiagnosis":[238],"X-ray":[240],"or":[241,342],"computed":[242],"tomography":[243],"images":[244],"(primarily":[245],"due":[246],"confusion":[248],"regarding":[249],"left\u2013right":[250],"laterality),":[251],"difficulties":[253],"prioritizing":[255],"appropriate":[256],"actions":[257],"clinical":[259,322,340],"complex":[262],"contextual":[263],"information.":[264],"CONCLUSIONS:":[265],"Four":[266],"released":[268],"surpassed":[271],"95%":[273],"benchmark":[274],"JNME,":[277],"near-perfect":[280],"(approximately":[281],"99%)":[282],"basic":[285],"highlights":[289],"substantial":[290,329],"use":[293,335],"learning":[295],"foundational":[298],"demonstrated":[304],"most":[306],"consistent":[307],"across":[309],"types,":[311],"while":[312],"Grok-4":[313],"showed":[314],"greater":[315],"variability.":[316],"concentration":[318],"incorrectness":[320],"indicates":[324],"that":[325],"still":[327],"require":[328],"refinement":[330],"validation":[332],"before":[333],"can":[336],"be":[337],"extended":[338],"reasoning":[341],"patient":[343],"care.":[344]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2026-02-04T00:00:00"}