{"id":"https://openalex.org/W7128399719","doi":"https://doi.org/10.5281/zenodo.18530700","title":"Evaluating Large Language Models on the 2026 Korean CSAT Mathematics Exam: Measuring Mathematical Ability in a Zero\u2013Data-Leakage Setting","display_name":"Evaluating Large Language Models on the 2026 Korean CSAT Mathematics Exam: Measuring Mathematical Ability in a Zero\u2013Data-Leakage Setting","publication_year":2025,"publication_date":"2025-11-13","ids":{"openalex":"https://openalex.org/W7128399719","doi":"https://doi.org/10.5281/zenodo.18530700"},"language":"ko","primary_location":{"id":"doi:10.5281/zenodo.18530700","doi":"https://doi.org/10.5281/zenodo.18530700","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.18530700","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"Dataset"},"volume":null,"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.18530700","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120058644","display_name":"Goun Pyeon","orcid":"https://orcid.org/0009-0004-2420-5956","observed_orcids":["https://orcid.org/0009-0004-2420-5956"]},"institutions":[{"id":"https://openalex.org/I196345858","display_name":"Chungnam National University","ror":"https://ror.org/0227as991","country_code":"KR","type":"education","lineage":["https://openalex.org/I196345858"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Pyeon, Goun","raw_affiliation_strings":["Chungnam National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chungnam National University","institution_ids":["https://openalex.org/I196345858"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120058645","display_name":"Inbum Heo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I196345858","display_name":"Chungnam National University","ror":"https://ror.org/0227as991","country_code":"KR","type":"education","lineage":["https://openalex.org/I196345858"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Heo, Inbum","raw_affiliation_strings":["Chungnam National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chungnam National University","institution_ids":["https://openalex.org/I196345858"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052038058","display_name":"Jeesu Jung","orcid":"https://orcid.org/0000-0003-1684-0517","observed_orcids":["https://orcid.org/0000-0003-1684-0517"]},"institutions":[{"id":"https://openalex.org/I196345858","display_name":"Chungnam National University","ror":"https://ror.org/0227as991","country_code":"KR","type":"education","lineage":["https://openalex.org/I196345858"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jung, Jeesu","raw_affiliation_strings":["Chungnam National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chungnam National University","institution_ids":["https://openalex.org/I196345858"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019368530","display_name":"Taewook Hwang","orcid":"https://orcid.org/0000-0003-2440-4707","observed_orcids":["https://orcid.org/0000-0003-2440-4707"]},"institutions":[{"id":"https://openalex.org/I196345858","display_name":"Chungnam National University","ror":"https://ror.org/0227as991","country_code":"KR","type":"education","lineage":["https://openalex.org/I196345858"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hwang, Taewook","raw_affiliation_strings":["Chungnam National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chungnam National University","institution_ids":["https://openalex.org/I196345858"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008607281","display_name":"Hyuk Namgoong","orcid":"https://orcid.org/0000-0001-5166-3064","observed_orcids":["https://orcid.org/0000-0001-5166-3064"]},"institutions":[{"id":"https://openalex.org/I196345858","display_name":"Chungnam National University","ror":"https://ror.org/0227as991","country_code":"KR","type":"education","lineage":["https://openalex.org/I196345858"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Namgoong, Hyuk","raw_affiliation_strings":["Chungnam National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chungnam National University","institution_ids":["https://openalex.org/I196345858"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014880875","display_name":"Hyein Seo","orcid":"https://orcid.org/0000-0003-3107-0880","observed_orcids":["https://orcid.org/0000-0003-3107-0880"]},"institutions":[{"id":"https://openalex.org/I196345858","display_name":"Chungnam National University","ror":"https://ror.org/0227as991","country_code":"KR","type":"education","lineage":["https://openalex.org/I196345858"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seo, Hyein","raw_affiliation_strings":["Chungnam National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chungnam National University","institution_ids":["https://openalex.org/I196345858"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125376987","display_name":"Yerim Han","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I196345858","display_name":"Chungnam National University","ror":"https://ror.org/0227as991","country_code":"KR","type":"education","lineage":["https://openalex.org/I196345858"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Han, Yerim","raw_affiliation_strings":["Chungnam National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chungnam National University","institution_ids":["https://openalex.org/I196345858"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125378104","display_name":"Eunbin Kim","orcid":"https://orcid.org/0009-0008-2704-3752","observed_orcids":["https://orcid.org/0009-0008-2704-3752"]},"institutions":[{"id":"https://openalex.org/I196345858","display_name":"Chungnam National University","ror":"https://ror.org/0227as991","country_code":"KR","type":"education","lineage":["https://openalex.org/I196345858"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kim, Eunbin","raw_affiliation_strings":["Chungnam National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chungnam National University","institution_ids":["https://openalex.org/I196345858"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111843481","display_name":"Hongmei Kang","orcid":"https://orcid.org/0000-0002-2012-9624","observed_orcids":["https://orcid.org/0000-0002-2012-9624"]},"institutions":[{"id":"https://openalex.org/I196345858","display_name":"Chungnam National University","ror":"https://ror.org/0227as991","country_code":"KR","type":"education","lineage":["https://openalex.org/I196345858"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kang, Hyeonseok","raw_affiliation_strings":["Chungnam National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chungnam National University","institution_ids":["https://openalex.org/I196345858"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067724204","display_name":"Sangkeun Jung","orcid":"https://orcid.org/0000-0003-3531-0618","observed_orcids":["https://orcid.org/0000-0003-3531-0618"]},"institutions":[{"id":"https://openalex.org/I196345858","display_name":"Chungnam National University","ror":"https://ror.org/0227as991","country_code":"KR","type":"education","lineage":["https://openalex.org/I196345858"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jung, Sangkeun","raw_affiliation_strings":["Chungnam National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chungnam National University","institution_ids":["https://openalex.org/I196345858"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I196345858"],"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/T10028","display_name":"Topic Modeling","score":0.3452000021934509,"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":0.3452000021934509,"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/T12522","display_name":"Mathematics Education and Pedagogy","score":0.13050000369548798,"subfield":{"id":"https://openalex.org/subfields/2604","display_name":"Applied Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.0674000009894371,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9819999933242798},{"id":"https://openalex.org/keywords/mathematical-ability","display_name":"mathematical ability","score":0.4699999988079071},{"id":"https://openalex.org/keywords/image-prompts","display_name":"image prompts","score":0.3310000002384186},{"id":"https://openalex.org/keywords/prompt-language","display_name":"prompt language","score":0.6370000243186951},{"id":"https://openalex.org/keywords/llm-benchmarking","display_name":"LLM benchmarking","score":0.4230000078678131}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5199999809265137},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4456999897956848},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42149999737739563},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4203999936580658},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.41200000047683716},{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.3939000070095062},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.3896999955177307},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.38909998536109924},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.3547999858856201},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34139999747276306},{"id":"https://openalex.org/C2780129039","wikidata":"https://www.wikidata.org/wiki/Q1931107","display_name":"Section (typography)","level":2,"score":0.31299999356269836},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C46681722","wikidata":"https://www.wikidata.org/wiki/Q4725589","display_name":"Alias","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2718000113964081},{"id":"https://openalex.org/C47177190","wikidata":"https://www.wikidata.org/wiki/Q207137","display_name":"Curriculum","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.2531999945640564},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.18530700","doi":"https://doi.org/10.5281/zenodo.18530700","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.18530700","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"Dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.18530700","doi":"https://doi.org/10.5281/zenodo.18530700","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.18530700","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"Dataset"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"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/W6949265622","https://openalex.org/W6912029901","https://openalex.org/W7116827658","https://openalex.org/W4395065433","https://openalex.org/W7213744299","https://openalex.org/W7203707296","https://openalex.org/W7160135972","https://openalex.org/W7111960236","https://openalex.org/W4404781623","https://openalex.org/W4382765605"],"abstract_inverted_index":{"This":[0],"dataset":[1,54],"contains":[2],"inference":[3],"outputs":[4],"from":[5,46,208],"evaluating":[6],"36+":[7],"state-of-the-art":[8],"large":[9],"language":[10],"models":[11],"(LLMs)":[12],"on":[13,169],"the":[14,194,209],"2026":[15],"Korean":[16,82],"College":[17],"Scholastic":[18],"Ability":[19],"Test":[20],"(CSAT)":[21],"Mathematics":[22],"section":[23],"(\ud640\uc218\ud615,":[24],"Odd":[25],"Type).":[26],"The":[27,53,173,202],"exam":[28,171,176,203],"consists":[29],"of":[30],"46":[31],"problems:":[32],"22":[33],"common":[34],"problems":[35,43,177],"(Math":[36],"I":[37],"&":[38,48],"II)":[39],"and":[40,51,100,118,166,180,199],"24":[41],"elective":[42],"(8":[44],"each":[45],"Probability":[47],"Statistics,":[49],"Calculus,":[50],"Geometry).":[52],"includes":[55],"347":[56],"TSV":[57],"files":[58],"(3.72":[59],"MB":[60],"total):":[61],"338":[62],"per-model":[63],"result":[64,106],"files,":[65],"organized":[66],"by":[67,193],"experimental":[68],"condition:":[69],"Input":[70],"modality:":[71],"text_only,":[72],"image_only,":[73],"text_fig":[74],"(text":[75],"+":[76],"figure)":[77],"Prompt":[78],"language:":[79],"English":[80],"(en),":[81],"(ko)":[83],"Extended":[84],"thinking:":[85],"enabled":[86],"(on),":[87],"disabled":[88],"(off)":[89],"9":[90],"ablation":[91],"summary":[92],"tables":[93],"aggregating":[94],"accuracy,":[95],"score,":[96],"latency,":[97,114],"token":[98,116],"usage,":[99],"cost":[101],"across":[102],"all":[103],"conditions.":[104],"Each":[105],"file":[107],"records":[108],"per-problem:":[109],"model":[110],"answer,":[111],"correctness,":[112],"response":[113],"prompt/completion":[115],"counts,":[117],"timestamps.":[119],"Models":[120],"evaluated":[121],"include:":[122],"OpenAI":[123],"GPT-5":[124],"family":[125],"(GPT-5,":[126],"GPT-5-Mini,":[127],"GPT-5-Nano,":[128],"GPT-5-Codex),":[129],"Anthropic":[130],"Claude":[131],"(Opus":[132],"4.1,":[133],"Sonnet":[134],"4.5,":[135],"Haiku":[136],"4.5),":[137],"Google":[138],"Gemini":[139],"2.5":[140],"(Pro,":[141],"Flash),":[142],"xAI":[143],"Grok":[144,148],"4":[145,153],"(Grok":[146],"4,":[147],"4-Fast),":[149],"Qwen3-VL,":[150],"Meta":[151],"Llama":[152],"Maverick,":[154],"DeepSeek":[155],"R1/V3,":[156],"Mistral":[157],"Magistral,":[158],"Kimi":[159],"K2,":[160],"MiniMax":[161],"M2,":[162],"Nvidia":[163],"Nemotron,":[164],"GLM-4.6,":[165],"others.":[167],"Note":[168],"original":[170,174],"data:":[172],"CSAT":[175],"(text,":[178],"images,":[179],"answer":[181],"keys)":[182],"are":[183],"not":[184],"included":[185],"in":[186],"this":[187],"deposit":[188],"due":[189],"to":[190],"copyright":[191],"restrictions":[192],"Korea":[195],"Institute":[196],"for":[197],"Curriculum":[198],"Evaluation":[200],"(KICE).":[201],"materials":[204],"can":[205],"be":[206],"obtained":[207],"official":[210],"KICE":[211],"website":[212],"(https://www.suneung.re.kr).":[213]},"counts_by_year":[],"updated_date":"2026-09-25T08:18:29.962427","created_date":"2026-02-10T00:00:00"}
