{"id":"https://openalex.org/W4414742445","doi":"https://doi.org/10.18653/v1/2026.acl-long.888","title":"CodeJudgeBench: Benchmarking LLM-as-a-Judge for Coding Tasks","display_name":"CodeJudgeBench: Benchmarking LLM-as-a-Judge for Coding Tasks","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4414742445","doi":"https://doi.org/10.18653/v1/2026.acl-long.888"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-long.888","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.888","pdf_url":"https://aclanthology.org/2026.acl-long.888.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.888.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Hongchao Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongchao Jiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100333357","display_name":"Yiming Chen","orcid":"https://orcid.org/0009-0002-3658-2754"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yiming Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yushi Cao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yushi Cao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040508737","display_name":"Hung-yi Lee","orcid":"https://orcid.org/0000-0002-9654-5747"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hung-yi Lee","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5111887396","display_name":"Robby T. Tan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Robby T. Tan","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":0.00393219,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"19416","last_page":"19448"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13999","display_name":"Digital Rights Management and Security","score":0.9258000254631042,"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/T13999","display_name":"Digital Rights Management and Security","score":0.9258000254631042,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.9031999707221985},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.6579999923706055},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.5938000082969666},{"id":"https://openalex.org/keywords/randomness","display_name":"Randomness","score":0.5353000164031982},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4602999985218048},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3285999894142151}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.9031999707221985},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6987000107765198},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.6579999923706055},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.5938000082969666},{"id":"https://openalex.org/C125112378","wikidata":"https://www.wikidata.org/wiki/Q176640","display_name":"Randomness","level":2,"score":0.5353000164031982},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46160000562667847},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4602999985218048},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35100001096725464},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3285999894142151},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C148027188","wikidata":"https://www.wikidata.org/wiki/Q907375","display_name":"Unit testing","level":3,"score":0.3084000051021576},{"id":"https://openalex.org/C197640229","wikidata":"https://www.wikidata.org/wiki/Q2534066","display_name":"Predictability","level":2,"score":0.30550000071525574},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2996000051498413},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2551000118255615}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.888","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.888","pdf_url":"https://aclanthology.org/2026.acl-long.888.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:2507.10535","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.10535","pdf_url":"https://arxiv.org/pdf/2507.10535","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.2507.10535","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.10535","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.888","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.888","pdf_url":"https://aclanthology.org/2026.acl-long.888.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":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414742445.pdf","grobid_xml":"https://content.openalex.org/works/W4414742445.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"are":[4,126],"increasingly":[5],"used":[6,51],"not":[7],"only":[8],"to":[9,14,61,109,128],"generate":[10],"code,":[11],"but":[12],"also":[13],"judge":[15],"it:":[16],"comparing,":[17],"ranking,":[18],"or":[19,32],"scoring":[20],"competing":[21],"solutions.However,":[22],"their":[23],"reliability":[24],"in":[25],"this":[26],"evaluative":[27],"role":[28],"remains":[29],"poorly":[30],"understood.Inconsistent":[31],"flawed":[33],"judgments":[34],"can":[35,102],"undermine":[36],"benchmarks":[37],"and":[38,46,74,89,118,125,136,146],"distort":[39],"training":[40],"signals.This":[41],"paper":[42],"investigates":[43],"the":[44,80,144],"performance":[45,81],"robustness":[47,113,147],"of":[48,82,148],"LLMs":[49],"when":[50],"as":[52,131],"code":[53,70,72],"judges.We":[54],"introduce":[55],"CodeJudgeBench,":[56],"a":[57],"benchmark":[58,79],"explicitly":[59],"designed":[60],"evaluate":[62],"LLM-as-a-Judge":[63,84],"models":[64,99,107,121],"across":[65],"three":[66],"critical":[67],"coding":[68,152],"tasks:":[69],"generation,":[71],"repair,":[73],"unit":[75],"test":[76],"generation.We":[77],"comprehensively":[78],"26":[83],"models,":[85],"encompassing":[86],"general-purpose,":[87],"code-tuned,":[88],"reasoning":[90,98],"models.Our":[91],"empirical":[92],"findings":[93,139],"reveal":[94],"that":[95],"relatively":[96],"small":[97],"(e.g.,":[100],"Qwen3-8B)":[101],"outperform":[103],"much":[104],"larger":[105],"non-reasoning":[106],"up":[108],"70B.We":[110],"further":[111],"stress-test":[112],"by":[114],"applying":[115],"both":[116],"general":[117],"code-specific":[119],"perturbations.All":[120],"show":[122],"significant":[123],"instability":[124],"sensitive":[127],"changes":[129],"such":[130],"response":[132],"ordering,":[133],"variable":[134],"naming,":[135],"misleading":[137],"comments.These":[138],"highlight":[140],"serious":[141],"concerns":[142],"about":[143],"consistency":[145],"LLM-based":[149],"judges":[150],"for":[151],"tasks.":[153]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}