{"id":"https://openalex.org/W7159640047","doi":"https://doi.org/10.48550/arxiv.2604.27470","title":"HealthBench Professional: Evaluating Large Language Models on Real Clinician Chats","display_name":"HealthBench Professional: Evaluating Large Language Models on Real Clinician Chats","publication_year":2026,"publication_date":"2026-04-30","ids":{"openalex":"https://openalex.org/W7159640047","doi":"https://doi.org/10.48550/arxiv.2604.27470"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.27470","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.27470","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.27470","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134997818","display_name":"Rebecca Soskin Hicks","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hicks, Rebecca Soskin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134967180","display_name":"Mikhail Trofimov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Trofimov, Mikhail","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134989502","display_name":"Dominick Lim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lim, Dominick","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134990130","display_name":"Rahul K. Arora","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arora, Rahul K.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122366848","display_name":"Foivos Tsimpourlas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tsimpourlas, Foivos","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119870581","display_name":"Preston Bowman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bowman, Preston","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119870582","display_name":"Michael Sharman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sharman, Michael","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122762064","display_name":"Chi Tong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tong, Chi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134990281","display_name":"Kavin Karthik","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Karthik, Kavin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134936856","display_name":"Arnav Dugar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dugar, Arnav","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134982704","display_name":"Akshay Jagadeesh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jagadeesh, Akshay","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134945684","display_name":"Khaled Saab","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saab, Khaled","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134985438","display_name":"Johannes Heidecke","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heidecke, Johannes","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134978200","display_name":"Ashley Alexander","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexander, Ashley","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048216681","display_name":"Nate Gross","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gross, Nate","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5027454515","display_name":"Karan Singhal","orcid":"https://orcid.org/0000-0001-9002-7490"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Singhal, Karan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":16,"corresponding_author_ids":["https://openalex.org/A5134997818"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"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":0.9861999750137329,"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":0.9861999750137329,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.001500000013038516,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12574","display_name":"Clinical Reasoning and Diagnostic Skills","score":0.0008999999845400453,"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/rubric","display_name":"Rubric","score":0.8052999973297119},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.5536999702453613},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5509999990463257},{"id":"https://openalex.org/keywords/health-care","display_name":"Health care","score":0.4878999888896942},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4602000117301941},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.3935999870300293},{"id":"https://openalex.org/keywords/patient-care","display_name":"Patient care","score":0.3310000002384186},{"id":"https://openalex.org/keywords/medline","display_name":"MEDLINE","score":0.3280999958515167}],"concepts":[{"id":"https://openalex.org/C111640148","wikidata":"https://www.wikidata.org/wiki/Q847349","display_name":"Rubric","level":2,"score":0.8052999973297119},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.661899983882904},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.5536999702453613},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5509999990463257},{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.4878999888896942},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4602000117301941},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42590001225471497},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.3935999870300293},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3716000020503998},{"id":"https://openalex.org/C2989236134","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Patient care","level":2,"score":0.3310000002384186},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.3280999958515167},{"id":"https://openalex.org/C509550671","wikidata":"https://www.wikidata.org/wiki/Q126945","display_name":"Medical education","level":1,"score":0.3197000026702881},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.319599986076355},{"id":"https://openalex.org/C184356942","wikidata":"https://www.wikidata.org/wiki/Q830382","display_name":"Best practice","level":2,"score":0.31869998574256897},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3068000078201294},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2957000136375427},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2928999960422516},{"id":"https://openalex.org/C2779974597","wikidata":"https://www.wikidata.org/wiki/Q28448986","display_name":"Clinical Practice","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C2778571376","wikidata":"https://www.wikidata.org/wiki/Q1355821","display_name":"Frontier","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C2779328685","wikidata":"https://www.wikidata.org/wiki/Q1475557","display_name":"Patient safety","level":3,"score":0.26190000772476196},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.25519999861717224}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.27470","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.27470","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.27470","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.27470","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"score":0.8349608778953552,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Millions":[0],"of":[1,11,45,116,135,141,149],"clinicians":[2,38,211],"use":[3,15,55],"ChatGPT":[4,41,76,175],"to":[5,40,58,112,131,198,214],"support":[6],"clinical":[7,59,205],"care,":[8],"but":[9],"evaluations":[10],"the":[12,43,132,192],"most":[13],"common":[14,54],"cases":[16,56],"in":[17,42,174,203],"model-clinician":[18],"conversations":[19],"are":[20],"limited.":[21],"We":[22,187],"introduce":[23],"HealthBench":[24,96,189],"Professional,":[25],"an":[26],"open":[27],"benchmark":[28,49],"for":[29,77,102,107,120,161,176],"evaluating":[30],"large":[31],"language":[32],"models":[33,123],"on":[34],"real":[35],"tasks":[36,163,206],"that":[37,210],"bring":[39],"course":[44],"their":[46],"work.":[47],"The":[48,169],"is":[50,80],"organized":[51],"around":[52],"three":[53,89,94],"central":[57],"practice:":[60],"care":[61],"consult,":[62],"writing":[63],"and":[64,66,79,85,105,184,207],"documentation,":[65],"medical":[67],"research.":[68],"Each":[69],"example":[70],"includes":[71],"a":[72,152,196],"physician-authored":[73],"conversation":[74],"with":[75],"Clinicians":[78],"scored":[81],"via":[82],"rubrics":[83],"written":[84],"iteratively":[86],"adjudicated":[87],"by":[88,126],"or":[90],"more":[91],"physicians":[92,144],"across":[93],"phases.":[95],"Professional":[97,190],"examples":[98,119,142],"were":[99,124],"carefully":[100],"selected":[101],"quality,":[103],"representativeness,":[104],"difficulty":[106],"OpenAI's":[108],"current":[109],"frontier":[110,200],"models,":[111,183],"enable":[113],"continued":[114],"measurement":[115],"progress.":[117],"Difficult":[118],"recent":[121],"OpenAI":[122],"enriched":[125],"roughly":[127],"3.5":[128],"times":[129],"relative":[130],"candidate":[133],"pool":[134],"15,079":[136],"examples.":[137],"Additionally,":[138],"about":[139],"one-third":[140],"involve":[143],"conducting":[145],"deliberate":[146],"adversarial":[147],"testing":[148],"models.":[150],"As":[151],"strong":[153],"baseline,":[154],"we":[155],"also":[156],"collected":[157],"human":[158,185],"physician":[159],"responses":[160],"all":[162,181],"(unbounded":[164],"time,":[165],"specialist-matched,":[166],"web":[167],"access).":[168],"best":[170],"scoring":[171],"system,":[172],"GPT-5.4":[173],"Clinicians,":[177],"outperforms":[178],"base":[179],"GPT-5.4,":[180],"other":[182],"physicians.":[186],"hope":[188],"provides":[191],"healthcare":[193],"AI":[194],"community":[195],"measure":[197],"track":[199],"model":[201],"progress":[202],"real-world":[204],"build":[208],"systems":[209],"can":[212],"trust":[213],"improve":[215],"care.":[216]},"counts_by_year":[],"updated_date":"2026-05-02T06:10:54.344120","created_date":"2026-05-02T00:00:00"}