{"id":"https://openalex.org/W4415539120","doi":"https://doi.org/10.1145/3746027.3758240","title":"MathScape: Benchmarking Multimodal Large Language Models in Real-World Mathematical Contexts","display_name":"MathScape: Benchmarking Multimodal Large Language Models in Real-World Mathematical Contexts","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415539120","doi":"https://doi.org/10.1145/3746027.3758240"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3758240","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3758240","pdf_url":null,"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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3758240","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112681217","display_name":"Hao Liang","orcid":"https://orcid.org/0009-0000-2963-2210"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hao Liang","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-2963-2210","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114231662","display_name":"Linzhuang Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linzhuang Sun","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0363-3607","affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120132024","display_name":"zhouminxuan zhouminxuan","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"zhouminxuan zhouminxuan","raw_affiliation_strings":["Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0006-5416-3157","affiliations":[{"raw_affiliation_string":"Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066109736","display_name":"Zirong Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zirong Chen","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-6907-8289","affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120132025","display_name":"Meiyi Qiang","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210095659","display_name":"Peking University Stomatological Hospital","ror":"https://ror.org/00s2xkh70","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210095659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meiyi Qiang","raw_affiliation_strings":["Peking University, Beijing, Bei Jing, China"],"raw_orcid":"https://orcid.org/0009-0009-3009-2886","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, Bei Jing, China","institution_ids":["https://openalex.org/I20231570","https://openalex.org/I4210095659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102576702","display_name":"Mingan Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingan Lin","raw_affiliation_strings":["Baichuan Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-2104-4641","affiliations":[{"raw_affiliation_string":"Baichuan Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028392096","display_name":"T. Li","orcid":null},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianpeng Li","raw_affiliation_strings":["Baichuan Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-1651-955X","affiliations":[{"raw_affiliation_string":"Baichuan Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Fan Yang","orcid":"https://orcid.org/0009-0001-0817-6508"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Yang","raw_affiliation_strings":["Baichuan Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-0817-6508","affiliations":[{"raw_affiliation_string":"Baichuan Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113005953","display_name":"Zenan Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zenan Zhou","raw_affiliation_strings":["Baichuan Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-5562-9604","affiliations":[{"raw_affiliation_string":"Baichuan Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008772211","display_name":"Wentao Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wentao Zhang","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7532-5550","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5112681217"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31230083,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12942","last_page":"12948"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9032999873161316,"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"}},"topics":[{"id":"https://openalex.org/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9032999873161316,"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/benchmarking","display_name":"Benchmarking","score":0.7735000252723694},{"id":"https://openalex.org/keywords/lagging","display_name":"Lagging","score":0.6477000117301941},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5975000262260437},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5371000170707703},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.48809999227523804},{"id":"https://openalex.org/keywords/mathematical-model","display_name":"Mathematical model","score":0.45159998536109924}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7735000252723694},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7028999924659729},{"id":"https://openalex.org/C2776962539","wikidata":"https://www.wikidata.org/wiki/Q6472078","display_name":"Lagging","level":2,"score":0.6477000117301941},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5975000262260437},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5371000170707703},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5194000005722046},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.48809999227523804},{"id":"https://openalex.org/C76969082","wikidata":"https://www.wikidata.org/wiki/Q486902","display_name":"Mathematical model","level":2,"score":0.45159998536109924},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.41749998927116394},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.4133000075817108},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36579999327659607},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.35659998655319214},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.32760000228881836},{"id":"https://openalex.org/C130327152","wikidata":"https://www.wikidata.org/wiki/Q748349","display_name":"Mathematical structure","level":2,"score":0.311599999666214},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3758240","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3758240","pdf_url":null,"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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:doi:10.48550/arxiv.2408.07543","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1145/3746027.3758240","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3758240","pdf_url":null,"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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4572520933","display_name":null,"funder_award_id":"92470121","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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,51,69,107,181,186],"rapid":[2],"progress":[3],"of":[4,29,53,71,183,189],"Multimodal":[5],"LLMs,":[6],"evaluating":[7],"their":[8],"mathematical":[9,22,92,191],"reasoning":[10,23,88],"capabilities":[11],"has":[12],"become":[13],"an":[14,30],"increasingly":[15],"important":[16],"research":[17],"direction.":[18],"In":[19],"particular,":[20],"visual-textual":[21],"serves":[24],"as":[25,45],"a":[26,81,116],"key":[27],"indicator":[28],"MLLM's":[31],"ability":[32,89],"to":[33],"comprehend":[34],"and":[35,47,64,133],"solve":[36],"complex,":[37],"multi-step":[38],"quantitative":[39],"problems.":[40],"While":[41],"existing":[42],"benchmarks":[43],"such":[44],"MathVista":[46],"MathVerse":[48],"have":[49],"advanced":[50],"evaluation":[52,119],"multimodal":[54,190],"math":[55,98,147],"proficiency,":[56],"they":[57],"primarily":[58],"rely":[59],"on":[60,85,165,176],"digitally":[61,168],"rendered":[62,169],"content":[63],"fall":[65],"short":[66],"in":[67,90,110,155,185],"capturing":[68],"complexity":[70],"real-world":[72,103,146,177],"scenarios.":[73],"To":[74],"bridge":[75],"this":[76],"gap,":[77],"we":[78,160],"introduce":[79],"MathScape,":[80],"novel":[82],"benchmark":[83],"focused":[84],"assessing":[86],"MLLMs'":[87],"realistic":[91],"contexts.":[93],"MathScape":[94,184],"comprises":[95],"1,369":[96],"high-quality":[97],"problems":[99],"paired":[100],"with":[101,128,145],"human-captured":[102],"images,":[104],"closely":[105],"reflecting":[106],"challenges":[108],"encountered":[109],"practical":[111],"educational":[112],"settings.":[113],"We":[114],"conduct":[115],"thorough":[117],"multi-dimensional":[118],"across":[120],"nine":[121],"leading":[122],"closed-source":[123],"MLLMs,":[124],"three":[125],"open-source":[126],"MLLMs":[127],"over":[129],"20":[130],"billion":[131],"parameters,":[132],"seven":[134],"smaller-scale":[135],"MLLMs.":[136],"Our":[137],"results":[138],"show":[139],"that":[140,162],"even":[141],"SOTA":[142],"models":[143],"struggle":[144],"tasks,":[148],"lagging":[149],"behind":[150],"human":[151],"performance-highlighting":[152],"critical":[153],"limitations":[154],"current":[156],"model":[157],"capabilities.":[158],"Moreover,":[159],"find":[161],"strong":[163],"performance":[164],"synthetic":[166],"or":[167],"images":[170],"does":[171],"not":[172],"guarantee":[173],"similar":[174],"effectiveness":[175],"tasks.":[178],"This":[179],"underscores":[180],"necessity":[182],"next":[187],"stage":[188],"reasoning.":[192]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-25T00:00:00"}