{"id":"https://openalex.org/W7125755380","doi":"https://doi.org/10.1145/3786181.3788710","title":"RuberDuckBench: A Benchmark for AI Coding Assistants","display_name":"RuberDuckBench: A Benchmark for AI Coding Assistants","publication_year":2026,"publication_date":"2026-04-12","ids":{"openalex":"https://openalex.org/W7125755380","doi":"https://doi.org/10.1145/3786181.3788710"},"language":null,"primary_location":{"id":"doi:10.1145/3786181.3788710","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786181.3788710","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 3rd International Workshop on Large Language Models For Code","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3786181.3788710","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123861203","display_name":"Ferida Mohammad","orcid":null},"institutions":[{"id":"https://openalex.org/I102373834","display_name":"Bryn Mawr College","ror":"https://ror.org/05sjwtp51","country_code":"US","type":"education","lineage":["https://openalex.org/I102373834"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ferida Mohammed","raw_affiliation_strings":["Bryn Mawr College, Bryn Mawr, PA, USA"],"raw_orcid":"https://orcid.org/0009-0004-5474-2322","affiliations":[{"raw_affiliation_string":"Bryn Mawr College, Bryn Mawr, PA, USA","institution_ids":["https://openalex.org/I102373834"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074064348","display_name":"Fatma Zohra Ayad","orcid":null},"institutions":[{"id":"https://openalex.org/I102373834","display_name":"Bryn Mawr College","ror":"https://ror.org/05sjwtp51","country_code":"US","type":"education","lineage":["https://openalex.org/I102373834"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fatma Ayad","raw_affiliation_strings":["Bryn Mawr College, Bryn Mawr, PA, USA"],"raw_orcid":"https://orcid.org/0009-0005-2803-176X","affiliations":[{"raw_affiliation_string":"Bryn Mawr College, Bryn Mawr, PA, USA","institution_ids":["https://openalex.org/I102373834"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102725147","display_name":"Petros Maniatis","orcid":"https://orcid.org/0000-0003-3777-5291"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Petros Maniatis","raw_affiliation_strings":["Google DeepMind, Mountain View, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-3777-5291","affiliations":[{"raw_affiliation_string":"Google DeepMind, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104084134","display_name":"Satish Chandra","orcid":"https://orcid.org/0000-0001-7625-4726"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Satish Chandra","raw_affiliation_strings":["Meta Platforms, Mountain View, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-2546-9000","affiliations":[{"raw_affiliation_string":"Meta Platforms, Mountain View, CA, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063180853","display_name":"Elizabeth Dinella","orcid":"https://orcid.org/0000-0003-0738-8813"},"institutions":[{"id":"https://openalex.org/I102373834","display_name":"Bryn Mawr College","ror":"https://ror.org/05sjwtp51","country_code":"US","type":"education","lineage":["https://openalex.org/I102373834"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elizabeth Dinella","raw_affiliation_strings":["Bryn Mawr College, Bryn Mawr, PA, USA"],"raw_orcid":"https://orcid.org/0000-0003-0738-8813","affiliations":[{"raw_affiliation_string":"Bryn Mawr College, Bryn Mawr, PA, USA","institution_ids":["https://openalex.org/I102373834"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":0.06467738,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"113","last_page":"120"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.20430000126361847,"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":0.20430000126361847,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.09570000320672989,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10533","display_name":"Teaching and Learning Programming","score":0.07769999653100967,"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/benchmark","display_name":"Benchmark (surveying)","score":0.8064000010490417},{"id":"https://openalex.org/keywords/rubric","display_name":"Rubric","score":0.7475000023841858},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.6870999932289124},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5533000230789185},{"id":"https://openalex.org/keywords/hallucinating","display_name":"Hallucinating","score":0.48590001463890076},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.462799996137619},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.40779998898506165}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8064000010490417},{"id":"https://openalex.org/C111640148","wikidata":"https://www.wikidata.org/wiki/Q847349","display_name":"Rubric","level":2,"score":0.7475000023841858},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7408000230789185},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6870999932289124},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5533000230789185},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5184999704360962},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5048999786376953},{"id":"https://openalex.org/C2911011789","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Hallucinating","level":2,"score":0.48590001463890076},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.462799996137619},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.40779998898506165},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.39590001106262207},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3921999931335449},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.3716999888420105},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3368000090122223},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3163999915122986},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.31220000982284546},{"id":"https://openalex.org/C184356942","wikidata":"https://www.wikidata.org/wiki/Q830382","display_name":"Best practice","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.2944999933242798},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2615000009536743}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3786181.3788710","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786181.3788710","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 3rd International Workshop on Large Language Models For Code","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2601.16456","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2601.16456","pdf_url":"https://arxiv.org/pdf/2601.16456","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3786181.3788710","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786181.3788710","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 3rd International Workshop on Large Language Models For Code","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Programmers":[0],"are":[1,14],"turning":[2],"to":[3,7,16,90,178],"AI":[4,189],"coding":[5,190],"assistants":[6],"answer":[8],"questions":[9,37,55,142],"about":[10,56],"their":[11,23],"code.":[12],"Benchmarks":[13],"needed":[15],"soundly":[17],"evaluate":[18,66],"these":[19,78],"systems":[20],"and":[21,105,172,187],"understand":[22],"performance.":[24,173],"To":[25],"enable":[26],"such":[27],"a":[28,32,51,67,180],"study,":[29],"we":[30,48],"curate":[31],"benchmark":[33,53,177],"of":[34,45,54,70,85,156],"real-world":[35],"contextualized":[36],"derived":[38],"from":[39],"Github":[40],"pull":[41],"request":[42],"comments.":[43],"Out":[44],"this":[46,176],"work,":[47],"present":[49],"RubberDuckBench:":[50],"multilingual":[52],"code,":[57],"along":[58],"with":[59,132,152],"detailed":[60],"rubrics":[61],"for":[62,182],"evaluating":[63],"answers.":[64],"We":[65,80,174],"diverse":[68],"set":[69],"20":[71],"LLMs":[72],"(proprietary":[73],"&":[74],"open-source)":[75],"on":[76,158],"answering":[77,138],"questions.":[79],"find":[81],"that":[82],"even":[83],"state":[84],"the":[86,96,119,133],"art":[87],"models":[88,126,136,149],"fail":[89],"give":[91],"consistent,":[92],"correct":[93,188],"responses":[94,157],"across":[95,145],"benchmark.":[97],"Grok":[98],"4":[99,103],"(69.29%),":[100],"Claude":[101],"Opus":[102],"(68.5%),":[104],"GPT-5":[106],"(67.8%)":[107],"perform":[108],"best":[109,122,134],"overall,":[110],"but":[111],"do":[112],"not":[113],"exhibit":[114],"pairwise":[115],"significant":[116],"superiority":[117],"over":[118],"next":[120],"9":[121],"performing":[123,135],"models.":[124],"Most":[125],"obtain":[127],"points":[128],"through":[129],"partial":[130],"credit,":[131],"only":[137],"at":[139],"most":[140],"2":[141],"completely":[143],"correctly":[144],"all":[146],"trials.":[147],"Furthermore,":[148],"often":[150],"hallucinate":[151],"lies":[153],"in":[154,185],"58.3%":[155],"average.":[159],"Cost":[160],"analysis":[161],"reveals":[162],"no":[163],"correlation":[164],"between":[165],"expense":[166],"(API":[167],"pricing":[168],"or":[169],"parameter":[170],"count)":[171],"intend":[175],"be":[179],"target":[181],"future":[183],"research":[184],"trustworthy":[186],"assistants.":[191]},"counts_by_year":[],"updated_date":"2026-07-08T06:22:20.291053","created_date":"2026-01-27T00:00:00"}