{"id":"https://openalex.org/W7204179395","doi":"https://doi.org/10.48550/arxiv.2608.22529","title":"Benchmarking the Titans: A Multi-Dimensional Empirical Evaluation of LLM Code Generation Quality in the .NET Ecosystem","display_name":"Benchmarking the Titans: A Multi-Dimensional Empirical Evaluation of LLM Code Generation Quality in the .NET Ecosystem","publication_year":2026,"publication_date":"2026-08-23","ids":{"openalex":"https://openalex.org/W7204179395","doi":"https://doi.org/10.48550/arxiv.2608.22529"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.22529","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22529","pdf_url":"https://arxiv.org/pdf/2608.22529","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":"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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.22529","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5148152181","display_name":"Seyed Mohammad Mahdi Ghalandarian","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I158248296","display_name":"Amirkabir University of Technology","ror":"https://ror.org/04gzbav43","country_code":"IR","type":"education","lineage":["https://openalex.org/I158248296"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Ghalandarian, Seyed Mohammad Mahdi","raw_affiliation_strings":["Amirkabir University of Technology , Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amirkabir University of Technology , Iran","institution_ids":["https://openalex.org/I158248296"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148148520","display_name":"Majid Bazargani","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I158248296","display_name":"Amirkabir University of Technology","ror":"https://ror.org/04gzbav43","country_code":"IR","type":"education","lineage":["https://openalex.org/I158248296"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Bazargani, Majid","raw_affiliation_strings":["Amirkabir University of Technology , Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amirkabir University of Technology , Iran","institution_ids":["https://openalex.org/I158248296"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033757604","display_name":"Masoumeh Taromirad","orcid":"https://orcid.org/0000-0002-0838-928X","observed_orcids":["https://orcid.org/0000-0002-0838-928X"]},"institutions":[{"id":"https://openalex.org/I158248296","display_name":"Amirkabir University of Technology","ror":"https://ror.org/04gzbav43","country_code":"IR","type":"education","lineage":["https://openalex.org/I158248296"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Taromirad, Masoumeh","raw_affiliation_strings":["Amirkabir University of Technology , Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amirkabir University of Technology , Iran","institution_ids":["https://openalex.org/I158248296"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I158248296"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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":0.9994999766349792,"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":0.9994999766349792,"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/T10430","display_name":"Software Engineering Techniques and Practices","score":0.00019999999494757503,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/llm-based-code-generation","display_name":"LLM-based code generation","score":0.9599999785423279},{"id":"https://openalex.org/keywords/c-code-generation","display_name":"C code generation","score":0.8420000076293945},{"id":"https://openalex.org/keywords/multidimensional-assessment","display_name":"multidimensional assessment","score":0.6439999938011169},{"id":"https://openalex.org/keywords/functional-correctness","display_name":"functional correctness","score":0.7599999904632568},{"id":"https://openalex.org/keywords/runtime-efficiency","display_name":"runtime efficiency","score":0.9800000190734863},{"id":"https://openalex.org/keywords/humaneval","display_name":"HumanEval","score":0.6629999876022339},{"id":"https://openalex.org/keywords/automated-unit-testing","display_name":"automated unit testing","score":0.7749999761581421},{"id":"https://openalex.org/keywords/gpt","display_name":"GPT","score":0.6240000128746033},{"id":"https://openalex.org/keywords/gemini","display_name":"Gemini","score":0.847000002861023},{"id":"https://openalex.org/keywords/claude","display_name":"Claude","score":0.984000027179718},{"id":"https://openalex.org/keywords/grok","display_name":"Grok","score":0.9350000023841858},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.4819999933242798}],"concepts":[{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.8859000205993652},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.828499972820282},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7562000155448914},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.6248999834060669},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.6026999950408936},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5989999771118164},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.5214999914169312},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.4918000102043152},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.49079999327659607},{"id":"https://openalex.org/C148027188","wikidata":"https://www.wikidata.org/wiki/Q907375","display_name":"Unit testing","level":3,"score":0.4821999967098236},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.424699991941452},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.37220001220703125},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3508000075817108},{"id":"https://openalex.org/C2777561058","wikidata":"https://www.wikidata.org/wiki/Q2652119","display_name":"Program comprehension","level":4,"score":0.3301999866962433},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.329800009727478},{"id":"https://openalex.org/C137287247","wikidata":"https://www.wikidata.org/wiki/Q1329550","display_name":"Static program analysis","level":4,"score":0.3199000060558319},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2888000011444092},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C97686452","wikidata":"https://www.wikidata.org/wiki/Q7604153","display_name":"Static analysis","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C98183937","wikidata":"https://www.wikidata.org/wiki/Q2112188","display_name":"Program analysis","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.2667999863624573},{"id":"https://openalex.org/C53942775","wikidata":"https://www.wikidata.org/wiki/Q1211721","display_name":"Code coverage","level":3,"score":0.2651999890804291},{"id":"https://openalex.org/C122637931","wikidata":"https://www.wikidata.org/wiki/Q118084","display_name":"Unit (ring theory)","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C509989072","wikidata":"https://www.wikidata.org/wiki/Q15188241","display_name":"Model-driven architecture","level":4,"score":0.2612999975681305},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C150292731","wikidata":"https://www.wikidata.org/wiki/Q1342704","display_name":"Code review","level":5,"score":0.2522999942302704}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.22529","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22529","pdf_url":"https://arxiv.org/pdf/2608.22529","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":"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"},{"id":"doi:10.48550/arxiv.2608.22529","doi":"https://doi.org/10.48550/arxiv.2608.22529","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.22529","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.22529","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22529","pdf_url":"https://arxiv.org/pdf/2608.22529","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":"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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204179395.pdf","grobid_xml":"https://content.openalex.org/works/W7204179395.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W2038214150","https://openalex.org/W3025993830","https://openalex.org/W3177813494","https://openalex.org/W3195140297","https://openalex.org/W4320003957","https://openalex.org/W4327810158","https://openalex.org/W4376166851","https://openalex.org/W4388502443","https://openalex.org/W4392679398","https://openalex.org/W4402835407","https://openalex.org/W4405903187","https://openalex.org/W4411523078","https://openalex.org/W4411552165","https://openalex.org/W7123341831"],"related_works":["https://openalex.org/W7219885475","https://openalex.org/W7221976040","https://openalex.org/W7133788408","https://openalex.org/W7168828084","https://openalex.org/W7130587547","https://openalex.org/W7172498920","https://openalex.org/W4412703849","https://openalex.org/W7164863649","https://openalex.org/W7214890797","https://openalex.org/W4401662005"],"abstract_inverted_index":{"Evaluating":[0],"Large":[1],"Language":[2],"Model":[3],"(LLM)":[4],"code":[5,15,88,137],"generation":[6],"quality":[7,138,160],"requires":[8],"examining":[9],"not":[10],"just":[11],"whether":[12,19],"the":[13,62,172],"generated":[14],"is":[16,21,61,124],"correct,":[17],"but":[18],"it":[20,91],"maintainable,":[22],"efficient,":[23],"and":[24,55,73,99,114,143,159],"stylistically":[25],"sound,":[26],"all":[27],"of":[28,32],"which":[29,48,121],"are":[30],"qualities":[31],"direct":[33],"importance":[34],"to":[35,43,92],"software":[36,178],"engineering":[37,179],"practitioners.":[38],"Existing":[39],"benchmarks":[40],"reduce":[41],"evaluation":[42,84],"a":[44,103,154],"single":[45],"Pass@k":[46,168],"metric,":[47],"obscures":[49],"critical":[50],"trade-offs":[51],"between":[52,157],"functional":[53,130],"correctness":[54,131,158],"structural":[56],"quality.":[57],"A":[58],"further":[59,182],"limitation":[60],"near-exclusive":[63],"focus":[64],"on":[65],"Python,":[66],"leaving":[67],"enterprise-relevant":[68],"ecosystems":[69],"such":[70],"as":[71],"C#":[72,87],".NET":[74],"without":[75],"dedicated":[76],"evaluation.":[77],"This":[78],"paper":[79],"presents":[80],"an":[81],"automated,":[82],"multi-dimensional":[83],"framework":[85],"for":[86],"generation,":[89],"applying":[90],"four":[93],"state-of-the-art":[94],"LLMs:":[95],"GPT,":[96],"Gemini,":[97],"Claude,":[98],"Grok.":[100],"We":[101,181],"conduct":[102],"controlled":[104],"experiment":[105],"across":[106,126],"85":[107],"algorithmic":[108],"tasks":[109],"derived":[110],"from":[111],"HumanEval,":[112],"generating":[113],"evaluating":[115],"340":[116],"solutions":[117],"in":[118,120,177],"total,":[119],"each":[122],"solution":[123],"assessed":[125],"three":[127],"independent":[128],"dimensions:":[129],"via":[132,139,146],"automated":[133],"unit":[134],"testing,":[135],"static":[136],"Roslyn":[140],"AST":[141],"analysis,":[142],"runtime":[144],"efficiency":[145],"adversarial":[147],"BenchmarkDotNet":[148],"profiling.":[149],"Our":[150],"central":[151],"finding":[152],"reveals":[153],"substantial":[155],"gap":[156],"attributes":[161],"(Pearson":[162],"r":[163],"=":[164],"0.075),":[165],"demonstrating":[166],"that":[167],"rankings":[169],"systematically":[170],"misrepresent":[171],"full":[173],"LLM":[174],"performance":[175],"profile":[176],"contexts.":[180],"characterize":[183],"GPT's":[184],"bimodal":[185],"failure":[186],"behavior.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-26T00:00:00"}
