{"id":"https://openalex.org/W4416420775","doi":"https://doi.org/10.3929/ethz-c-000794529","title":"Proof or Bluff? Evaluating LLMs on 2025 USA Math Olympiad","display_name":"Proof or Bluff? Evaluating LLMs on 2025 USA Math Olympiad","publication_year":2025,"publication_date":"2025-03-27","ids":{"openalex":"https://openalex.org/W4416420775","doi":"https://doi.org/10.3929/ethz-c-000794529"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2503.21934","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.21934","pdf_url":"https://arxiv.org/pdf/2503.21934","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/2503.21934","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081872880","display_name":"Ivo Petrov","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Petrov, Ivo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093356429","display_name":"Jasper Dekoninck","orcid":"https://orcid.org/0009-0009-0621-170X","observed_orcids":["https://orcid.org/0009-0009-0621-170X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dekoninck, Jasper","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120415333","display_name":"Lyuben Baltadzhiev","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Baltadzhiev, Lyuben","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119958090","display_name":"Maria Drencheva","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Drencheva, Maria","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120500053","display_name":"Kristian Minchev","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minchev, Kristian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018338894","display_name":"Mislav Balunovi\u0107","orcid":"https://orcid.org/0000-0002-7024-7688","observed_orcids":["https://orcid.org/0000-0002-7024-7688"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Balunovi\u0107, Mislav","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006417702","display_name":"Nikola M. Jovanovi\u0107","orcid":"https://orcid.org/0000-0003-0185-2304","observed_orcids":["https://orcid.org/0000-0003-0185-2304"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jovanovi\u0107, Nikola","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5069901599","display_name":"Martin Vechev","orcid":"https://orcid.org/0000-0002-0054-9568","observed_orcids":["https://orcid.org/0000-0002-0054-9568"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vechev, Martin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"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/T10028","display_name":"Topic Modeling","score":0.4634000062942505,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.4634000062942505,"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.16500000655651093,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T13904","display_name":"Artificial Intelligence Applications","score":0.0877000018954277,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9769999980926514},{"id":"https://openalex.org/keywords/mathematical-reasoning","display_name":"mathematical reasoning","score":0.8930000066757202},{"id":"https://openalex.org/keywords/proof-generation","display_name":"proof generation","score":0.9549999833106995},{"id":"https://openalex.org/keywords/manual-annotation","display_name":"manual annotation","score":0.4309999942779541},{"id":"https://openalex.org/keywords/failure-modes","display_name":"failure modes","score":0.8090000152587891},{"id":"https://openalex.org/keywords/mathematics-competitions","display_name":"mathematics competitions","score":0.44999998807907104},{"id":"https://openalex.org/keywords/llm-benchmark","display_name":"LLM benchmark","score":0.4970000088214874}],"concepts":[{"id":"https://openalex.org/C130383907","wikidata":"https://www.wikidata.org/wiki/Q221956","display_name":"Olympiad","level":2,"score":0.7903000116348267},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.46720001101493835},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4560000002384186},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.4147999882698059},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.3855000138282776},{"id":"https://openalex.org/C76969082","wikidata":"https://www.wikidata.org/wiki/Q486902","display_name":"Mathematical model","level":2,"score":0.38109999895095825},{"id":"https://openalex.org/C47884741","wikidata":"https://www.wikidata.org/wiki/Q1166618","display_name":"Mathematical logic","level":2,"score":0.3440999984741211},{"id":"https://openalex.org/C97364631","wikidata":"https://www.wikidata.org/wiki/Q484284","display_name":"Deductive reasoning","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.30410000681877136},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2955999970436096},{"id":"https://openalex.org/C53537400","wikidata":"https://www.wikidata.org/wiki/Q140637","display_name":"Numeracy","level":3,"score":0.29260000586509705},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2741999924182892},{"id":"https://openalex.org/C2992562121","wikidata":"https://www.wikidata.org/wiki/Q3817808","display_name":"Scientific reasoning","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.25130000710487366}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:arXiv.org:2503.21934","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.21934","pdf_url":"https://arxiv.org/pdf/2503.21934","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":"pmh:oai:www.research-collection.ethz.ch:20.500.11850/794529","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11850/794529","pdf_url":null,"source":{"id":"https://openalex.org/S4306402302","display_name":"Repository for Publications and Research Data (ETH Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I35440088","host_organization_name":"ETH Zurich","host_organization_lineage":["https://openalex.org/I35440088"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.2503.21934","doi":"https://doi.org/10.48550/arxiv.2503.21934","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.21934","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.3929/ethz-c-000794529","doi":"https://doi.org/10.3929/ethz-c-000794529","is_oa":true,"landing_page_url":"https://doi.org/10.3929/ethz-c-000794529","pdf_url":null,"source":{"id":"https://openalex.org/S7407051236","display_name":"ETH Z\u00fcrich Research Collection","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Other"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.21934","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.21934","pdf_url":"https://arxiv.org/pdf/2503.21934","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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7103139038","https://openalex.org/W4409399840","https://openalex.org/W4416610439","https://openalex.org/W7160095038","https://openalex.org/W4403365207","https://openalex.org/W6891891353","https://openalex.org/W4407719116","https://openalex.org/W7127397879","https://openalex.org/W4414814585","https://openalex.org/W7168281436"],"abstract_inverted_index":{"Recent":[0],"math":[1],"benchmarks":[2,38],"for":[3,56,71,159,167],"large":[4],"language":[5],"models":[6,15,40,84,104,118],"(LLMs)":[7],"such":[8],"as":[9],"MathArena":[10],"indicate":[11],"that":[12,101,154],"state-of-the-art":[13,82],"reasoning":[14,49,70,83,127,162,171],"achieve":[16,119],"impressive":[17],"performance":[18],"on":[19,43,85],"mathematical":[20,58,73,161],"competitions":[21],"like":[22],"AIME,":[23],"with":[24],"the":[25,86,90,131,143,165],"leading":[26],"model,":[27],"Gemini-2.5-Pro,":[28],"achieving":[29],"scores":[30],"comparable":[31],"to":[32],"top":[33],"human":[34,77],"competitors.":[35],"However,":[36],"these":[37],"evaluate":[39],"solely":[41],"based":[42],"final":[44],"numerical":[45],"answers,":[46],"neglecting":[47],"rigorous":[48,160],"and":[50,136,172],"proof":[51,173],"generation":[52,174],"which":[53],"are":[54,157],"essential":[55],"real-world":[57],"tasks.":[59],"To":[60],"address":[61],"this,":[62],"we":[63,79,129],"introduce":[64],"a":[65,110],"comprehensive":[66],"evaluation":[67],"of":[68,95,113,126],"full-solution":[69],"challenging":[72],"problems.":[74],"Using":[75],"expert":[76],"annotators,":[78],"evaluated":[80],"several":[81,138],"six":[87],"problems":[88],"from":[89,142],"2025":[91],"USAMO":[92],"within":[93],"hours":[94],"their":[96],"release.":[97],"Our":[98],"results":[99,152],"reveal":[100],"all":[102,116],"tested":[103],"struggled":[105],"significantly:":[106],"only":[107],"Gemini-2.5-Pro":[108],"achieves":[109],"non-trivial":[111],"score":[112],"25%,":[114],"while":[115],"other":[117],"less":[120],"than":[121],"5%.":[122],"Through":[123],"detailed":[124],"analysis":[125],"traces,":[128],"identify":[130],"most":[132],"common":[133],"failure":[134],"modes":[135],"find":[137],"unwanted":[139],"artifacts":[140],"arising":[141],"optimization":[144],"strategies":[145],"employed":[146],"during":[147],"model":[148],"training.":[149],"Overall,":[150],"our":[151],"suggest":[153],"current":[155],"LLMs":[156],"inadequate":[158],"tasks,":[163],"highlighting":[164],"need":[166],"substantial":[168],"improvements":[169],"in":[170],"capabilities.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-09-22T06:50:58.402377","created_date":"2025-10-10T00:00:00"}
