{"id":{"repo_id":"vilnius","oai_identifier":"oai:vu.lt:elaba:210646955"},"canonical_url":"https://search.ndltd.org/etd/vilnius/oai:vu.lt:elaba:210646955","repository":{"repo_id":"vilnius","name":"Vilnius University","base_url":"https://epublications.vu.lt/oai"},"display":{"title":"Didelių kalbos modelių sugeneruoto kodo kokybės vertinimas /","abstract":"These days it is very popular to do a variety of assignments using artificial intelligence. The driving force behind all AI tools is large language models. Using large language models many results can be achieved, although tools like „ChatGPT“ or „Google Gemini“ ar used specifically for problem solving. Studens often use these tools as sources of information while completing assignments, these tools are also used in many projects in an attempt to optimize the usage of their human resources. Large language models can perform many feats, but how well can they generate code? The goal of this study is to figure out how well large language models can generate code when given different instructions and wether or not they can do it better than an expert programmer. After completing the study it can be said that large language models are not as good as generating code as an expert programmer is at writing it. Depending on the assignment that they are given, they can generate code that does not work at all. The most reliable and highest quality code out of the three evaluated models was generated by the „GPT-4“ model which was created by „OpenAI“.","abstract_html":"These days it is very popular to do a variety of assignments using artificial intelligence. The driving force behind all AI tools is large language models. Using large language models many results can be achieved, although tools like „ChatGPT“ or „Google Gemini“ ar used specifically for problem solving. Studens often use these tools as sources of information while completing assignments, these tools are also used in many projects in an attempt to optimize the usage of their human resources. Large language models can perform many feats, but how well can they generate code? The goal of this study is to figure out how well large language models can generate code when given different instructions and wether or not they can do it better than an expert programmer. After completing the study it can be said that large language models are not as good as generating code as an expert programmer is at writing it. Depending on the assignment that they are given, they can generate code that does not work at all. The most reliable and highest quality code out of the three evaluated models was generated by the „GPT-4“ model which was created by „OpenAI“.","abstract_has_math":false,"creators":["Ivoška, Julius,"],"institution":"Institutional Repository of Vilnius University","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024","date_published":"2024","updated_at":"2026-11-19T10:10:16Z","subjects":[],"languages":["lit"],"rights":["info:eu-repo/semantics/openAccess"],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://repository.vu.lt/VU:ELABAETD210646955&prefLang=en_US","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://repository.vu.lt/VU:ELABAETD210646955&prefLang=en_US","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":"open","embargo_until":null,"access_note":null},"source_record":{"url":"https://epublications.vu.lt/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai%3Avu.lt%3Aelaba%3A210646955","prefix":"oai_dc"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Ivoška, Julius,"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2024"]},{"key":"dc:publisher","label":"Institution","values":["Institutional Repository of Vilnius University"]},{"key":"dc:relation","label":"Dc Relation","values":["https://epublications.vu.lt/object/elaba:210646955/210646955.pdf"]},{"key":"dc:type","label":"Dc Type","values":["info:eu-repo/semantics/bachelorThesis"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["lit"]},{"key":"dc:rights","label":"Dc Rights","values":["info:eu-repo/semantics/openAccess"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://repository.vu.lt/VU:ELABAETD210646955&prefLang=en_US"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["These days it is very popular to do a variety of assignments using artificial intelligence. The driving force behind all AI tools is large language models. Using large language models many results can be achieved, although tools like „ChatGPT“ or „Google Gemini“ ar used specifically for problem solving. Studens often use these tools as sources of information while completing assignments, these tools are also used in many projects in an attempt to optimize the usage of their human resources. Large language models can perform many feats, but how well can they generate code? The goal of this study is to figure out how well large language models can generate code when given different instructions and wether or not they can do it better than an expert programmer. After completing the study it can be said that large language models are not as good as generating code as an expert programmer is at writing it. Depending on the assignment that they are given, they can generate code that does not work at all. The most reliable and highest quality code out of the three evaluated models was generated by the „GPT-4“ model which was created by „OpenAI“."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Didelių kalbos modelių sugeneruoto kodo kokybės vertinimas /","Evaluation of code generated by large language models."]}]}],"canonical_facts":{"dc:creator":["Ivoška, Julius,"],"dc:date":["2024"],"dc:description":["These days it is very popular to do a variety of assignments using artificial intelligence. The driving force behind all AI tools is large language models. Using large language models many results can be achieved, although tools like „ChatGPT“ or „Google Gemini“ ar used specifically for problem solving. Studens often use these tools as sources of information while completing assignments, these tools are also used in many projects in an attempt to optimize the usage of their human resources. Large language models can perform many feats, but how well can they generate code? The goal of this study is to figure out how well large language models can generate code when given different instructions and wether or not they can do it better than an expert programmer. After completing the study it can be said that large language models are not as good as generating code as an expert programmer is at writing it. Depending on the assignment that they are given, they can generate code that does not work at all. The most reliable and highest quality code out of the three evaluated models was generated by the „GPT-4“ model which was created by „OpenAI“."],"dc:format":["application/pdf"],"dc:identifier":["https://repository.vu.lt/VU:ELABAETD210646955&prefLang=en_US"],"dc:language":["lit"],"dc:publisher":["Institutional Repository of Vilnius University"],"dc:relation":["https://epublications.vu.lt/object/elaba:210646955/210646955.pdf"],"dc:rights":["info:eu-repo/semantics/openAccess"],"dc:title":["Didelių kalbos modelių sugeneruoto kodo kokybės vertinimas /","Evaluation of code generated by large language models."],"dc:type":["info:eu-repo/semantics/bachelorThesis"]},"updated_at":"2026-11-19T10:10:16Z"}