{"id":"https://openalex.org/W4416868356","doi":"https://doi.org/10.48550/arxiv.2508.09101","title":"AutoCodeBench: Large Language Models are Automatic Code Benchmark Generators","display_name":"AutoCodeBench: Large Language Models are Automatic Code Benchmark Generators","publication_year":2025,"publication_date":"2025-08-12","ids":{"openalex":"https://openalex.org/W4416868356","doi":"https://doi.org/10.48550/arxiv.2508.09101"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2508.09101","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.09101","pdf_url":"https://arxiv.org/pdf/2508.09101","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/2508.09101","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Chou, Jason","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chou, Jason","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100346418","display_name":"Ao Liu","orcid":"https://orcid.org/0000-0002-8412-6414","observed_orcids":["https://orcid.org/0000-0002-8412-6414","https://orcid.org/0009-0001-3171-0350"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Ao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Deng, Yuchi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deng, Yuchi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114123750","display_name":"Zhiying Zeng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeng, Zhiying","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100375823","display_name":"Tao Zhang","orcid":"https://orcid.org/0000-0002-6272-4069","observed_orcids":["https://orcid.org/0000-0002-6272-4069"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Tao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107956203","display_name":"Haotian Zhu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Haotian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102377998","display_name":"Jianwei Cai","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cai, Jianwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052943433","display_name":"Yue Mao","orcid":"https://orcid.org/0000-0003-4680-9916","observed_orcids":["https://orcid.org/0000-0003-4680-9916"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mao, Yue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100408851","display_name":"Chenchen Zhang","orcid":"https://orcid.org/0000-0003-0458-6232","observed_orcids":["https://orcid.org/0000-0003-0458-6232"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Chenchen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053443014","display_name":"Lingyun Tan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tan, Lingyun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100527194","display_name":"Ziyan Xu","orcid":"https://orcid.org/0000-0002-2986-8466","observed_orcids":["https://orcid.org/0000-0002-2986-8466","https://orcid.org/0009-0001-7055-9788"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Ziyan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120489312","display_name":"Bohui Zhai","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhai, Bohui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004929949","display_name":"Haijing Liu","orcid":"https://orcid.org/0009-0000-4772-9569","observed_orcids":["https://orcid.org/0009-0000-4772-9569"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Hengyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhu, Speed","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Speed","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhou, Wiggin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Wiggin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5091705422","display_name":"Fengzong Lian","orcid":"https://orcid.org/0000-0002-9871-3038","observed_orcids":["https://orcid.org/0000-0002-9871-3038"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lian, Fengzong","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":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/T10260","display_name":"Software Engineering Research","score":0.9907000064849854,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10260","display_name":"Software Engineering Research","score":0.9907000064849854,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10028","display_name":"Topic Modeling","score":0.003700000001117587,"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/T10533","display_name":"Teaching and Learning Programming","score":0.002300000051036477,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/code-generation-benchmarks","display_name":"code generation benchmarks","score":0.6809999942779541},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7699999809265137},{"id":"https://openalex.org/keywords/multilingual-code-generation","display_name":"multilingual code generation","score":0.7860000133514404},{"id":"https://openalex.org/keywords/test-case-generation","display_name":"test case generation","score":0.8230000138282776},{"id":"https://openalex.org/keywords/programming-languages","display_name":"programming languages","score":0.6010000109672546}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7955999970436096},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6793000102043152},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.6111999750137329},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5715000033378601},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.5605000257492065},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.48559999465942383},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4672999978065491},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.43779999017715454},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.34439998865127563},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C168725872","wikidata":"https://www.wikidata.org/wiki/Q991663","display_name":"Sophistication","level":2,"score":0.322299987077713},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3037000000476837},{"id":"https://openalex.org/C128942645","wikidata":"https://www.wikidata.org/wiki/Q1568346","display_name":"Test case","level":3,"score":0.3027999997138977},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.2962999939918518},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.29319998621940613},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2786000072956085},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.26589998602867126}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2508.09101","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.09101","pdf_url":"https://arxiv.org/pdf/2508.09101","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.2508.09101","doi":"https://doi.org/10.48550/arxiv.2508.09101","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.09101","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.09101","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.09101","pdf_url":"https://arxiv.org/pdf/2508.09101","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":[],"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":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4,24],"demonstrated":[5],"remarkable":[6],"capabilities":[7],"across":[8,53,154],"various":[9],"domains,":[10],"with":[11,114,198],"code":[12,30,95,146,221,247],"generation":[13,31,96,132,147,222,248],"emerging":[14],"as":[15,231],"a":[16,121,144,232],"key":[17],"area":[18],"of":[19,107,205],"focus.":[20],"While":[21],"numerous":[22],"benchmarks":[23,34,63,72],"been":[25],"proposed":[26],"to":[27,51,162,217,239],"evaluate":[28,163,173],"their":[29,219],"abilities,":[32],"these":[33,83,206],"face":[35],"several":[36],"critical":[37],"limitations.":[38],"First,":[39],"they":[40],"often":[41],"rely":[42],"on":[43,66,165,181,241],"manual":[44,99],"annotations,":[45],"which":[46],"are":[47],"time-consuming":[48],"and":[49,57,77,105,116,133,168,178,183,202,235,244],"difficult":[50],"scale":[52],"different":[54],"programming":[55,156],"languages":[56],"problem":[58,131],"complexities.":[59],"Second,":[60],"most":[61,194],"existing":[62],"focus":[64,240],"primarily":[65],"Python,":[67],"while":[68,124],"the":[69,103,193,199,226,237],"few":[70],"multilingual":[71,94,122,170,203,246],"suffer":[73],"from":[74],"limited":[75],"difficulty":[76],"uneven":[78],"language":[79],"distribution.":[80],"To":[81],"address":[82],"challenges,":[84],"we":[85,141,209],"propose":[86],"AutoCodeGen,":[87],"an":[88],"automated":[89],"method":[90],"for":[91,214],"generating":[92,111],"high-difficulty":[93],"datasets":[97],"without":[98],"annotations.":[100],"AutoCodeGen":[101],"ensures":[102],"correctness":[104],"completeness":[106],"test":[108,112,118],"cases":[109],"by":[110],"inputs":[113],"LLMs":[115,164,180,196],"obtaining":[117],"outputs":[119],"through":[120,129],"sandbox,":[123],"achieving":[125],"high":[126],"data":[127],"quality":[128],"reverse-order":[130],"multiple":[134],"filtering":[135],"steps.":[136],"Using":[137],"this":[138],"novel":[139],"method,":[140],"introduce":[142,210],"AutoCodeBench,":[143],"large-scale":[145],"benchmark":[148],"comprising":[149],"3,920":[150],"problems":[151],"evenly":[152],"distributed":[153],"20":[155],"languages.":[157],"It":[158],"is":[159],"specifically":[160,212],"designed":[161,213],"challenging,":[166],"diverse,":[167],"practical":[169,245],"tasks.":[171,207],"We":[172,224],"over":[174],"30":[175],"leading":[176],"open-source":[177],"proprietary":[179],"AutoCodeBench":[182,227],"its":[184],"simplified":[185],"version":[186],"AutoCodeBench-Lite.":[187],"The":[188],"results":[189],"show":[190],"that":[191],"even":[192],"advanced":[195],"struggle":[197],"complexity,":[200],"diversity,":[201],"nature":[204],"Besides,":[208],"AutoCodeBench-Complete,":[211],"base":[215],"models":[216],"assess":[218],"few-shot":[220],"capabilities.":[223],"hope":[225],"series":[228],"will":[229],"serve":[230],"valuable":[233],"resource":[234],"inspire":[236],"community":[238],"more":[242],"challenging":[243],"scenarios.":[249]},"counts_by_year":[],"updated_date":"2026-10-05T09:50:58.205359","created_date":"2025-10-10T00:00:00"}
