{"id":"https://openalex.org/W4415062494","doi":"https://doi.org/10.18653/v1/2026.acl-long.792","title":"Challenging the Boundaries of Reasoning: An Olympiad-Level Math Benchmark for Large Language Models","display_name":"Challenging the Boundaries of Reasoning: An Olympiad-Level Math Benchmark for Large Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4415062494","doi":"https://doi.org/10.18653/v1/2026.acl-long.792"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-long.792","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.792","pdf_url":"https://aclanthology.org/2026.acl-long.792.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.792.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101395445","display_name":"Haoxiang Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haoxiang Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059541770","display_name":"Yingqian Min","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yingqian Min","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066988400","display_name":"Zhipeng Chen","orcid":"https://orcid.org/0009-0009-4875-5465"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhipeng Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037145565","display_name":"Wayne Xin Zhao","orcid":"https://orcid.org/0000-0002-8333-6196"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5143187583","display_name":"Ji-Rong Wen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ji-Rong Wen","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01145271,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"17438","last_page":"17457"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9049000144004822,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9049000144004822,"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/benchmark","display_name":"Benchmark (surveying)","score":0.5789999961853027},{"id":"https://openalex.org/keywords/mathematical-model","display_name":"Mathematical model","score":0.4366999864578247},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.3982999920845032},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.38999998569488525},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3799000084400177},{"id":"https://openalex.org/keywords/verifiable-secret-sharing","display_name":"Verifiable secret sharing","score":0.35839998722076416},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.35260000824928284},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.3450999855995178}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6714000105857849},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5789999961853027},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4571000039577484},{"id":"https://openalex.org/C76969082","wikidata":"https://www.wikidata.org/wiki/Q486902","display_name":"Mathematical model","level":2,"score":0.4366999864578247},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3982999920845032},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.38999998569488525},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3799000084400177},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.37700000405311584},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.35839998722076416},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.35260000824928284},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.3450999855995178},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3206000030040741},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.31839999556541443},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C130327152","wikidata":"https://www.wikidata.org/wiki/Q748349","display_name":"Mathematical structure","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C172347087","wikidata":"https://www.wikidata.org/wiki/Q3217196","display_name":"Language of mathematics","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C2776542497","wikidata":"https://www.wikidata.org/wiki/Q5266672","display_name":"Development (topology)","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C2777617010","wikidata":"https://www.wikidata.org/wiki/Q18957","display_name":"Mainstream","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C2779193601","wikidata":"https://www.wikidata.org/wiki/Q20026918","display_name":"Mathematical theory","level":2,"score":0.25209999084472656}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.792","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.792","pdf_url":"https://aclanthology.org/2026.acl-long.792.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.21380","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2503.21380","pdf_url":"https://arxiv.org/pdf/2503.21380","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,"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.2503.21380","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.21380","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.792","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.792","pdf_url":"https://aclanthology.org/2026.acl-long.792.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4128466783","display_name":null,"funder_award_id":"92470205","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415062494.pdf","grobid_xml":"https://content.openalex.org/works/W4415062494.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"rapid":[1],"advancement":[2],"of":[3],"large":[4],"reasoning":[5,145],"models":[6,130],"has":[7],"saturated":[8],"existing":[9],"math":[10,30],"benchmarks,":[11],"underscoring":[12],"the":[13,43,112],"urgent":[14],"need":[15],"for":[16,70,87],"more":[17],"challenging":[18],"evaluation":[19,49,58],"frameworks.To":[20],"address":[21],"this,":[22],"we":[23,142],"introduce":[24],"OlymMATH,":[25],"a":[26,52,147],"rigorously":[27],"curated,":[28],"Olympiad-level":[29],"benchmark":[31,45],"comprising":[32,63],"350":[33],"problems,":[34],"each":[35],"with":[36,67],"parallel":[37],"English":[38],"and":[39,61,74,105,116,126,150],"Chinese":[40],"versions.OlymMATH":[41],"is":[42],"first":[44],"to":[46,98],"unify":[47],"dual":[48],"paradigms":[50],"within":[51],"single":[53],"suite:":[54],"(1)":[55],"natural":[56],"language":[57],"through":[59,78],"OlymMATH-EASY":[60],"OlymMATH-HARD,":[62],"200":[64],"computational":[65],"problems":[66,82,91],"numerical":[68],"answers":[69],"objective":[71],"rule-based":[72],"assessment,":[73],"(2)":[75],"formal":[76],"verification":[77],"OlymMATH-LEAN,":[79],"offering":[80],"150":[81],"formalized":[83],"in":[84],"Lean":[85],"4":[86],"rigorous":[88,136],"process-level":[89],"evaluation.All":[90],"are":[92],"manually":[93],"sourced":[94],"from":[95],"printed":[96],"publications":[97],"minimize":[99],"data":[100],"contamination,":[101],"verified":[102],"by":[103],"experts,":[104],"span":[106],"four":[107],"core":[108],"domains.Extensive":[109],"experiments":[110],"reveal":[111],"benchmark's":[113],"significant":[114],"challenge,":[115],"our":[117],"analysis":[118],"also":[119],"uncovers":[120],"consistent":[121],"performance":[122],"gaps":[123],"between":[124],"languages":[125],"identifies":[127],"cases":[128],"where":[129],"employ":[131],"heuristic":[132],"\"guessing\"":[133],"rather":[134],"than":[135],"reasoning.To":[137],"further":[138],"support":[139],"community":[140],"research,":[141],"release":[143],"582k+":[144],"trajectories,":[146],"visualization":[148],"tool,":[149],"expert":[151],"solutions":[152],"at":[153],"https://github.com/RUCAIBox/OlymMATH.":[154]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-11T00:00:00"}