{"id":"https://openalex.org/W7124997329","doi":"https://doi.org/10.1109/aiware69974.2025.00035","title":"Where Do LLMs Still Struggle? An In-Depth Analysis of Code Generation Benchmarks","display_name":"Where Do LLMs Still Struggle? An In-Depth Analysis of Code Generation Benchmarks","publication_year":2025,"publication_date":"2025-11-19","ids":{"openalex":"https://openalex.org/W7124997329","doi":"https://doi.org/10.1109/aiware69974.2025.00035"},"language":"en","primary_location":{"id":"doi:10.1109/aiware69974.2025.00035","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aiware69974.2025.00035","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 2nd IEEE/ACM International Conference on AI-powered Software (AIware)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123406281","display_name":"Amir Molzam Sharifloo","orcid":null},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Amir Molzam Sharifloo","raw_affiliation_strings":["Technische Universit&#x00E4;t,Darmstadt,Germany"],"affiliations":[{"raw_affiliation_string":"Technische Universit&#x00E4;t,Darmstadt,Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120305264","display_name":"Maedeh Heydari","orcid":null},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Maedeh Heydari","raw_affiliation_strings":["Technische Universit&#x00E4;t,Darmstadt,Germany"],"affiliations":[{"raw_affiliation_string":"Technische Universit&#x00E4;t,Darmstadt,Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123439961","display_name":"Parsa Kazerooni","orcid":null},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Parsa Kazerooni","raw_affiliation_strings":["Technische Universit&#x00E4;t,Darmstadt,Germany"],"affiliations":[{"raw_affiliation_string":"Technische Universit&#x00E4;t,Darmstadt,Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093511552","display_name":"Daniel Maninger","orcid":"https://orcid.org/0009-0005-0649-4958"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Daniel Maninger","raw_affiliation_strings":["Technische Universit&#x00E4;t,Darmstadt,Germany"],"affiliations":[{"raw_affiliation_string":"Technische Universit&#x00E4;t,Darmstadt,Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123442293","display_name":"Mira Mezini","orcid":null},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mira Mezini","raw_affiliation_strings":["Technische Universit&#x00E4;t,Darmstadt,Germany"],"affiliations":[{"raw_affiliation_string":"Technische Universit&#x00E4;t,Darmstadt,Germany","institution_ids":["https://openalex.org/I31512782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5123406281"],"corresponding_institution_ids":["https://openalex.org/I31512782"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.66815756,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"249","last_page":"253"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.30000001192092896,"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"}},"topics":[{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.30000001192092896,"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/T10028","display_name":"Topic Modeling","score":0.1348000019788742,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.08320000022649765,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6051999926567078},{"id":"https://openalex.org/keywords/race","display_name":"Race (biology)","score":0.5794000029563904},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5134999752044678},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.42179998755455017},{"id":"https://openalex.org/keywords/strengths-and-weaknesses","display_name":"Strengths and weaknesses","score":0.3540000021457672}],"concepts":[{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6051999926567078},{"id":"https://openalex.org/C76509639","wikidata":"https://www.wikidata.org/wiki/Q918036","display_name":"Race (biology)","level":2,"score":0.5794000029563904},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5586000084877014},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5134999752044678},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.4641000032424927},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.42179998755455017},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.37599998712539673},{"id":"https://openalex.org/C63882131","wikidata":"https://www.wikidata.org/wiki/Q17122954","display_name":"Strengths and weaknesses","level":2,"score":0.3540000021457672},{"id":"https://openalex.org/C184356942","wikidata":"https://www.wikidata.org/wiki/Q830382","display_name":"Best practice","level":2,"score":0.3068999946117401},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.28949999809265137}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/aiware69974.2025.00035","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aiware69974.2025.00035","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 2nd IEEE/ACM International Conference on AI-powered Software (AIware)","raw_type":"proceedings-article"},{"id":"pmh:oai:tubiblio.ulb.tu-darmstadt.de:159509","is_oa":false,"landing_page_url":"http://tubiblio.ulb.tu-darmstadt.de/view/person/Sharifloo=3AAmir_Molzam=3A=3A.html>","pdf_url":null,"source":{"id":"https://openalex.org/S4377196390","display_name":"TUbilio (Technical University of Darmstadt)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I31512782","host_organization_name":"Technische Universit\u00e4t Darmstadt","host_organization_lineage":["https://openalex.org/I31512782"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"NonPeerReviewed"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W4411552824"],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4],"achieved":[5],"remarkable":[6],"success":[7],"in":[8,129],"code":[9,72,104],"generation,":[10],"and":[11,27,58],"the":[12,43,60,91,99],"race":[13],"to":[14,49,87,106,143],"improve":[15],"their":[16],"performance":[17],"has":[18],"become":[19],"a":[20,110],"central":[21],"focus":[22],"of":[23,35,62,93,102,113,127],"AI":[24],"research.":[25],"Benchmarks":[26],"leaderboards":[28],"are":[29,84],"increasingly":[30],"popular,":[31],"offering":[32],"quantitative":[33],"rankings":[34],"LLMs.":[36],"However,":[37],"they":[38],"provide":[39],"limited":[40],"insight":[41],"into":[42],"tasks":[44,74,115,138],"that":[45,51,81,116,139],"LLMs":[46,83,117],"consistently":[47,118],"fail":[48],"solve-information":[50],"is":[52],"crucial":[53],"for":[54],"understanding":[55],"current":[56],"limitations":[57],"guiding":[59],"development":[61],"more":[63],"capable":[64],"models.":[65],"To":[66,89],"address":[67],"this":[68],"gap,":[69],"we":[70,96],"examined":[71],"generation":[73],"across":[75],"four":[76,124],"popular":[77],"benchmarks,":[78],"identifying":[79],"those":[80],"major":[82],"most":[85,140],"likely":[86],"fail.":[88],"understand":[90],"causes":[92],"these":[94],"failures,":[95],"investigated":[97],"whether":[98],"static":[100],"complexity":[101],"solution":[103],"contributes":[105],"them,":[107],"followed":[108],"by":[109],"systematic":[111],"inspection":[112],"114":[114],"struggled":[119],"with.":[120],"Our":[121],"analysis":[122],"revealed":[123],"recurring":[125],"patterns":[126],"weaknesses":[128],"LLMs,":[130],"as":[131,133],"well":[132],"common":[134],"complications":[135],"within":[136],"benchmark":[137],"often":[141],"lead":[142],"failure.":[144]},"counts_by_year":[],"updated_date":"2026-02-26T08:16:20.718346","created_date":"2026-01-21T00:00:00"}
