{"id":"https://openalex.org/W7204449673","doi":"https://doi.org/10.48550/arxiv.2608.25071","title":"HealthBench-Psych: A Mental Health Subset of OpenAI's HealthBench","display_name":"HealthBench-Psych: A Mental Health Subset of OpenAI's HealthBench","publication_year":2026,"publication_date":"2026-08-25","ids":{"openalex":"https://openalex.org/W7204449673","doi":"https://doi.org/10.48550/arxiv.2608.25071"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.25071","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.25071","pdf_url":"https://arxiv.org/pdf/2608.25071","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.25071","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5098779094","display_name":"Matthew Flathers","orcid":"https://orcid.org/0009-0004-3351-0688","observed_orcids":["https://orcid.org/0009-0004-3351-0688"]},"institutions":[{"id":"https://openalex.org/I1316535847","display_name":"Beth Israel Deaconess Medical Center","ror":"https://ror.org/04drvxt59","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1316535847"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Flathers, Matthew","raw_affiliation_strings":["Division of Digital Psychiatry , Beth Israel Deaconess Medical Center , Boston , MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Digital Psychiatry , Beth Israel Deaconess Medical Center , Boston , MA","institution_ids":["https://openalex.org/I1316535847"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148414934","display_name":"Phuong Anh Nguyen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1316535847","display_name":"Beth Israel Deaconess Medical Center","ror":"https://ror.org/04drvxt59","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1316535847"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nguyen, Phuong Anh","raw_affiliation_strings":["Division of Digital Psychiatry , Beth Israel Deaconess Medical Center , Boston , MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Digital Psychiatry , Beth Israel Deaconess Medical Center , Boston , MA","institution_ids":["https://openalex.org/I1316535847"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135747773","display_name":"Jill Noorily","orcid":"https://orcid.org/0009-0005-8971-6551","observed_orcids":["https://orcid.org/0009-0005-8971-6551"]},"institutions":[{"id":"https://openalex.org/I1316535847","display_name":"Beth Israel Deaconess Medical Center","ror":"https://ror.org/04drvxt59","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1316535847"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Noorily, Jill","raw_affiliation_strings":["Division of Digital Psychiatry , Beth Israel Deaconess Medical Center , Boston , MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Digital Psychiatry , Beth Israel Deaconess Medical Center , Boston , MA","institution_ids":["https://openalex.org/I1316535847"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014916564","display_name":"Julian Herpertz","orcid":"https://orcid.org/0009-0003-8416-2970","observed_orcids":["https://orcid.org/0009-0003-8416-2970"]},"institutions":[{"id":"https://openalex.org/I1316535847","display_name":"Beth Israel Deaconess Medical Center","ror":"https://ror.org/04drvxt59","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1316535847"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Herpertz, Julian","raw_affiliation_strings":["Division of Digital Psychiatry , Beth Israel Deaconess Medical Center , Boston , MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Digital Psychiatry , Beth Israel Deaconess Medical Center , Boston , MA","institution_ids":["https://openalex.org/I1316535847"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148469502","display_name":"Meiting Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1316535847","display_name":"Beth Israel Deaconess Medical Center","ror":"https://ror.org/04drvxt59","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1316535847"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen, Meiting","raw_affiliation_strings":["Division of Digital Psychiatry , Beth Israel Deaconess Medical Center , Boston , MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Digital Psychiatry , Beth Israel Deaconess Medical Center , Boston , MA","institution_ids":["https://openalex.org/I1316535847"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148465908","display_name":"Jasreen Multani","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1316535847","display_name":"Beth Israel Deaconess Medical Center","ror":"https://ror.org/04drvxt59","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1316535847"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Multani, Jasreen","raw_affiliation_strings":["Division of Digital Psychiatry , Beth Israel Deaconess Medical Center , Boston , MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Digital Psychiatry , Beth Israel Deaconess Medical Center , Boston , MA","institution_ids":["https://openalex.org/I1316535847"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148417703","display_name":"Samuel Powell","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1316535847","display_name":"Beth Israel Deaconess Medical Center","ror":"https://ror.org/04drvxt59","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1316535847"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Powell, Samuel","raw_affiliation_strings":["Department of Psychiatry , Beth Israel Deaconess Medical Center , Boston , MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Psychiatry , Beth Israel Deaconess Medical Center , Boston , MA","institution_ids":["https://openalex.org/I1316535847"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120363338","display_name":"Mason Granof","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1316535847","display_name":"Beth Israel Deaconess Medical Center","ror":"https://ror.org/04drvxt59","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1316535847"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Granof, Mason","raw_affiliation_strings":["Division of Digital Psychiatry , Beth Israel Deaconess Medical Center , Boston , MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Digital Psychiatry , Beth Israel Deaconess Medical Center , Boston , MA","institution_ids":["https://openalex.org/I1316535847"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148450627","display_name":"Mark Kalinch","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1316535847","display_name":"Beth Israel Deaconess Medical Center","ror":"https://ror.org/04drvxt59","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1316535847"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kalinch, Mark","raw_affiliation_strings":["Division of Digital Psychiatry , Beth Israel Deaconess Medical Center , Boston , MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Digital Psychiatry , Beth Israel Deaconess Medical Center , Boston , MA","institution_ids":["https://openalex.org/I1316535847"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026523515","display_name":"John Blake Torous","orcid":"https://orcid.org/0000-0002-5362-7937","observed_orcids":["https://orcid.org/0000-0002-5362-7937"]},"institutions":[{"id":"https://openalex.org/I1316535847","display_name":"Beth Israel Deaconess Medical Center","ror":"https://ror.org/04drvxt59","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1316535847"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Torous, John","raw_affiliation_strings":["Division of Digital Psychiatry , Beth Israel Deaconess Medical Center , Boston , MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Digital Psychiatry , Beth Israel Deaconess Medical Center , Boston , MA","institution_ids":["https://openalex.org/I1316535847"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1316535847"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":0.9589999914169312,"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":0.9589999914169312,"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/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.005200000014156103,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12488","display_name":"Mental Health via Writing","score":0.003800000064074993,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/mental-health","display_name":"mental health","score":0.7850000262260437},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9330000281333923},{"id":"https://openalex.org/keywords/benchmark-dataset","display_name":"benchmark dataset","score":0.4090000092983246},{"id":"https://openalex.org/keywords/llm-evaluation","display_name":"LLM evaluation","score":0.6169999837875366},{"id":"https://openalex.org/keywords/llm-as-a-judge","display_name":"LLM-as-a-judge","score":0.5370000004768372},{"id":"https://openalex.org/keywords/psychological-support","display_name":"psychological support","score":0.3869999945163727}],"concepts":[{"id":"https://openalex.org/C44210515","wikidata":"https://www.wikidata.org/wiki/Q16968978","display_name":"Bespoke","level":2,"score":0.9039999842643738},{"id":"https://openalex.org/C134362201","wikidata":"https://www.wikidata.org/wiki/Q317309","display_name":"Mental health","level":2,"score":0.7501999735832214},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.6586999893188477},{"id":"https://openalex.org/C2778571376","wikidata":"https://www.wikidata.org/wiki/Q1355821","display_name":"Frontier","level":2,"score":0.5163999795913696},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.49720001220703125},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.49050000309944153},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4050999879837036},{"id":"https://openalex.org/C75630572","wikidata":"https://www.wikidata.org/wiki/Q538904","display_name":"Applied psychology","level":1,"score":0.38499999046325684},{"id":"https://openalex.org/C118552586","wikidata":"https://www.wikidata.org/wiki/Q7867","display_name":"Psychiatry","level":1,"score":0.36070001125335693},{"id":"https://openalex.org/C2982912361","wikidata":"https://www.wikidata.org/wiki/Q1851867","display_name":"Mental model","level":2,"score":0.35670000314712524},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.3345000147819519},{"id":"https://openalex.org/C509550671","wikidata":"https://www.wikidata.org/wiki/Q126945","display_name":"Medical education","level":1,"score":0.29100000858306885},{"id":"https://openalex.org/C138816342","wikidata":"https://www.wikidata.org/wiki/Q189603","display_name":"Public health","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C27415008","wikidata":"https://www.wikidata.org/wiki/Q7256382","display_name":"Psychological intervention","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C154874363","wikidata":"https://www.wikidata.org/wiki/Q3518464","display_name":"Medical classification","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C2779974597","wikidata":"https://www.wikidata.org/wiki/Q28448986","display_name":"Clinical Practice","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.25850000977516174},{"id":"https://openalex.org/C162118730","wikidata":"https://www.wikidata.org/wiki/Q1128453","display_name":"Actuarial science","level":1,"score":0.25209999084472656}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.25071","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.25071","pdf_url":"https://arxiv.org/pdf/2608.25071","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.25071","doi":"https://doi.org/10.48550/arxiv.2608.25071","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.25071","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.25071","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.25071","pdf_url":"https://arxiv.org/pdf/2608.25071","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","score":0.8999999761581421,"display_name":"Good health and well-being"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204449673.pdf","grobid_xml":"https://content.openalex.org/works/W7204449673.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4416245944","https://openalex.org/W4388748472","https://openalex.org/W4414801979","https://openalex.org/W7131883710","https://openalex.org/W7214671029","https://openalex.org/W7171745322","https://openalex.org/W7119510990","https://openalex.org/W4414591374","https://openalex.org/W7172034215","https://openalex.org/W7129067450"],"abstract_inverted_index":{"General-purpose":[0],"health":[1,26],"benchmarks":[2,49],"increasingly":[3],"anchor":[4],"claims":[5],"about":[6],"LLM":[7,111],"medical":[8],"performance,":[9],"but":[10],"they":[11],"are":[12,46,51],"not":[13],"always":[14],"resolved":[15],"by":[16],"clinical":[17],"specialty,":[18],"making":[19],"domain-specific":[20],"performance":[21],"hard":[22],"to":[23,37,53],"isolate.":[24],"Mental":[25],"is":[27],"of":[28,34,84,96,109],"acute":[29],"public-health":[30],"concern":[31],"as":[32,144],"millions":[33],"people":[35],"turn":[36],"LLMs":[38],"for":[39,69],"psychological":[40],"support,":[41],"and":[42,61,102,126,141],"most":[43],"existing":[44],"evaluations":[45],"bespoke":[47],"academic":[48],"that":[50],"difficult":[52],"integrate":[54],"into":[55],"developer":[56],"workflows.":[57],"We":[58,63,133],"introduce":[59],"HealthBench-Psych":[60],"HealthBench-Psych-Hard.":[62],"screened":[64],"HealthBench's":[65],"5,000":[66],"physician-rubric":[67],"conversations":[68,94],"mental-health":[70],"relevance":[71],"with":[72,88],"a":[73,106,115,145],"transparent":[74],"LLM-applied":[75],"rubric,":[76],"then":[77],"validated":[78],"the":[79,97,135],"subset":[80],"through":[81],"two":[82,124],"rounds":[83],"blinded":[85],"clinician":[86],"review":[87],"concealed":[89],"known-exclude":[90],"controls,":[91],"yielding":[92],"610":[93],"(12.2%":[95],"corpus).":[98],"Evaluating":[99],"20":[100],"frontier":[101,118],"open":[103],"models":[104],"under":[105],"cross-vendor":[107],"panel":[108],"three":[110],"judges,":[112],"we":[113],"find":[114],"statistically":[116],"tied":[117],"cluster,":[119],"measurable":[120],"refusal":[121],"behavior":[122],"in":[123],"models,":[125],"near-identical":[127],"rankings":[128],"across":[129],"judges":[130],"($\u03c4\\ge":[131],"0.92$).":[132],"release":[134],"subset,":[136],"pipeline,":[137],"model":[138],"responses,":[139],"grades,":[140],"analysis":[142],"code":[143],"reusable":[146],"resource.":[147]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-28T00:00:00"}
