{"id":"https://openalex.org/W7160553175","doi":"https://doi.org/10.1145/3786335.3813180","title":"Vibe Code Bench: Evaluating AI Models on End-to-End Web Application Development","display_name":"Vibe Code Bench: Evaluating AI Models on End-to-End Web Application Development","publication_year":2026,"publication_date":"2026-05-22","ids":{"openalex":"https://openalex.org/W7160553175","doi":"https://doi.org/10.1145/3786335.3813180"},"language":null,"primary_location":{"id":"doi:10.1145/3786335.3813180","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786335.3813180","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 ACM Conference on AI and Agentic Systems","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3786335.3813180","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135634226","display_name":"Hung Tran","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156590","display_name":"Vala Sciences (United States)","ror":"https://ror.org/05gr5bv62","country_code":"US","type":"company","lineage":["https://openalex.org/I4210156590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hung Tran","raw_affiliation_strings":["Vals AI, San Francisco, California, USA"],"raw_orcid":"https://orcid.org/0009-0005-6044-2067","affiliations":[{"raw_affiliation_string":"Vals AI, San Francisco, California, USA","institution_ids":["https://openalex.org/I4210156590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009459298","display_name":"Langston Nashold","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156590","display_name":"Vala Sciences (United States)","ror":"https://ror.org/05gr5bv62","country_code":"US","type":"company","lineage":["https://openalex.org/I4210156590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Langston Nashold","raw_affiliation_strings":["Vals AI, San Francisco, California, USA"],"raw_orcid":"https://orcid.org/0009-0008-6554-5198","affiliations":[{"raw_affiliation_string":"Vals AI, San Francisco, California, USA","institution_ids":["https://openalex.org/I4210156590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102786166","display_name":"Rayan Krishnan","orcid":"https://orcid.org/0000-0002-3481-020X"},"institutions":[{"id":"https://openalex.org/I4210156590","display_name":"Vala Sciences (United States)","ror":"https://ror.org/05gr5bv62","country_code":"US","type":"company","lineage":["https://openalex.org/I4210156590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rayan Krishnan","raw_affiliation_strings":["Vals AI, San Francisco, California, USA"],"raw_orcid":"https://orcid.org/0000-0002-3481-020X","affiliations":[{"raw_affiliation_string":"Vals AI, San Francisco, California, USA","institution_ids":["https://openalex.org/I4210156590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128234378","display_name":"Antoine Bigeard","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156590","display_name":"Vala Sciences (United States)","ror":"https://ror.org/05gr5bv62","country_code":"US","type":"company","lineage":["https://openalex.org/I4210156590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Antoine Bigeard","raw_affiliation_strings":["Vals AI, San Francisco, California, USA"],"raw_orcid":"https://orcid.org/0009-0008-4808-8028","affiliations":[{"raw_affiliation_string":"Vals AI, San Francisco, California, USA","institution_ids":["https://openalex.org/I4210156590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135622125","display_name":"Alex Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210110987","display_name":"IIT@MIT","ror":"https://ror.org/01wp8zh54","country_code":"US","type":"facility","lineage":["https://openalex.org/I30771326","https://openalex.org/I4210110987"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alex Gu","raw_affiliation_strings":["MIT, Cambridge, Massachusetts, USA"],"raw_orcid":"https://orcid.org/0000-0002-4814-0796","affiliations":[{"raw_affiliation_string":"MIT, Cambridge, Massachusetts, USA","institution_ids":["https://openalex.org/I4210110987"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"514","last_page":"536"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.4528000056743622,"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":0.4528000056743622,"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":0.21950000524520874,"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"}},{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.047200001776218414,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.7537999749183655},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6326000094413757},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.628600001335144},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5738999843597412},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.5659999847412109},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.5121999979019165},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5052000284194946},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4772999882698059}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7932000160217285},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7537999749183655},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6326000094413757},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.628600001335144},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5738999843597412},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.5659999847412109},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.5121999979019165},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5052000284194946},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4772999882698059},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.47380000352859497},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46549999713897705},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.45879998803138733},{"id":"https://openalex.org/C2778571376","wikidata":"https://www.wikidata.org/wiki/Q1355821","display_name":"Frontier","level":2,"score":0.4546999931335449},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.414900004863739},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3878999948501587},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.3732999861240387},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3668000102043152},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36250001192092896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35019999742507935},{"id":"https://openalex.org/C2776542497","wikidata":"https://www.wikidata.org/wiki/Q5266672","display_name":"Development (topology)","level":2,"score":0.31380000710487366},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.30979999899864197},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3093000054359436},{"id":"https://openalex.org/C11392498","wikidata":"https://www.wikidata.org/wiki/Q11288","display_name":"Web server","level":3,"score":0.2800999879837036},{"id":"https://openalex.org/C149672775","wikidata":"https://www.wikidata.org/wiki/Q8777","display_name":"Hypertext Transfer Protocol","level":3,"score":0.275299996137619},{"id":"https://openalex.org/C148027188","wikidata":"https://www.wikidata.org/wiki/Q907375","display_name":"Unit testing","level":3,"score":0.2721000015735626},{"id":"https://openalex.org/C199519371","wikidata":"https://www.wikidata.org/wiki/Q942695","display_name":"Source lines of code","level":3,"score":0.26899999380111694},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.25920000672340393}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3786335.3813180","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786335.3813180","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 ACM Conference on AI and Agentic Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2603.04601","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2603.04601","pdf_url":"https://arxiv.org/pdf/2603.04601","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:10.1145/3786335.3813180","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786335.3813180","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 ACM Conference on AI and Agentic Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Code":[0,33],"generation":[1],"has":[2],"emerged":[3],"as":[4],"one":[5],"of":[6,23,37],"AI\u2019s":[7],"highest-impact":[8],"use":[9],"cases,":[10],"yet":[11],"existing":[12],"benchmarks":[13],"measure":[14],"isolated":[15],"tasks":[16],"rather":[17],"than":[18],"the":[19],"complete":[20],"\"zero-to-one\"":[21],"process":[22],"building":[24],"a":[25,35],"working":[26],"application":[27,40],"from":[28],"scratch.":[29],"We":[30],"introduce":[31],"Vibe":[32],"Bench,":[34],"benchmark":[36],"100":[38],"web":[39],"specifications":[41],"(50":[42],"public":[43],"validation,":[44],"50":[45],"held-out":[46],"test)":[47],"with":[48],"964":[49],"browser-based":[50],"workflows":[51],"comprising":[52],"10,131":[53],"substeps,":[54],"evaluated":[55],"against":[56],"deployed":[57],"applications":[58],"by":[59],"an":[60],"autonomous":[61],"browser":[62],"agent.":[63]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-05-08T00:00:00"}
