[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-273433-105":59,"doc-detail-273433-en":131},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","plsqlbench-benchmarking-llm-systems-for-executable-procedural-database-programming","PLSQLBENCH - Benchmarking LLM Systems for Executable Procedural Database Programming","","PLSQLBENCH is a benchmark that evaluates whether large language models can write executable PL/SQL programs, using correctness determined by execution-based tests rather than text similarity. It targets procedural database programming, which remains underexplored compared with general code generation and declarative text-to-SQL benchmarks. The dataset includes 2,865 instances (single-turn and multi-turn conversations) with schema-grounded tasks drawn from Spider and MBPP-derived procedural problems. Experiments with eight LLMs show recurring challenges in schema grounding, PL/SQL dialect fidelity, control flow, exception handling, and cross-turn consistency, with tool-augmented agents improving results on some tasks.",{"@graph":69,"@context":123},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/plsqlbench-benchmarking-llm-systems-for-executable-procedural-database-programming/273433/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/plsqlbench-benchmarking-llm-systems-for-executable-procedural-database-programming/273433.png","ImageObject",300,407,{"name":92,"@type":93},"Lucas Martin","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-30","2026-09-15",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",21,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What does PLSQLBENCH measure for LLMs?","Question",{"text":113,"@type":114},"PLSQLBENCH evaluates whether LLMs can generate executable PL/SQL programs whose correctness is verified through execution-based tests.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How is the benchmark structured in terms of tasks and interactions?",{"text":118,"@type":114},"The benchmark includes 2,594 single-turn tasks and 271 multi-turn conversations totaling 978 turns, requiring generation, modification, debugging, validation, and repair.",{"name":120,"@type":111,"acceptedAnswer":121},"What difficulties do experiments reveal across LLMs?",{"text":122,"@type":114},"Experiments with eight LLMs show recurring problems with schema grounding, PL/SQL dialect fidelity, procedural control flow, exception handling, and consistency across conversation turns.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},273433,1789471409,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":130,"read_time":26,"preview_page_count":4},8796095360427,"https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d","PLSQLBENCH: Benchmarking LLM Systems for Executable Procedural  \nDatabase Programming  \nMarianne Menglin Liu1,* , Leonid Boytsov1,* , Daniel W. Peterson1 , Pramuditha Perera1 , Rongguang Wang1 , Sai Ashish Somayajula1 , Syed Hamza Rafique2 , Rohit Saini2 , Shubham Pathak2 , Sujeeth Bharadwaj1 , Tao Sheng1 , Graham Horwood1 , Fahad Shah1 , Ankan Bansal1 , Sujith Ravi1 , Dan Roth1  \n1 Oracle AI, 2Turing Enterprise Inc  \n*Equal contribution. Correspondence: {marianne.liu, leo.boytsov, [dan.roth}@oracle.com](dan.roth}@oracle.com)  \narXiv :2608 . 15931v1 [ cs .CL] 16 Aug 2026  \nAbstract  \nWe present PLSQLBENCH, to our knowledge the first benchmark for evaluating whether LLMs can write executable PL/SQL programs, with correctness measured through execution-based tests. Existing LLM evaluations largely target general-purpose code generation or declarative text-to-SQL, leaving procedural database programming underexplored. PLSQLBENCH contains 2,865 instances: 2,594 single-turn tasks and 271 multi-turn conversations spanning 978 turns. The benchmark combines complex schemagrounded tasks over enterprise-style Spider 2 databases, simpler schema-grounded tasks derived from Spider, and MBPP-derived procedural problems, covering varying levels of database grounding and procedural complexity. Experiments with eight LLMs reveal recurring difficulties in schema grounding, PL/SQL dialect fidelity, procedural control flow, exception handling, and cross-turn consistency. Toolaugmented LLM agents improve performance on several schema-grounded evaluations, although substantial gaps remain. These results highlight procedural database-programming capabilities not directly assessed by conventional code-generation or text-to-SQL benchmarks. Our code is available at [https://](https://)[ ](https://)[github.com/oracle-samples/plsqlbench](github.com/oracle-samples/plsqlbench).  \n1 Introduction  \nEnterprise database development often requires procedural database programming: creating reusable database-resident programs that combine SQL with procedural constructs such as variables, control flow, loops, cursors, and error handling. In production systems, these programs validate records, enforce business rules, log failures, coordinate transactions, and run scheduled maintenance tasks. Procedural programming over databases is supported across relational and cloud data platforms through procedural  \nSQL dialects, including GoogleSQL scripting in BigQuery, PL/pgSQL in PostgreSQL, Snowflake Scripting in Snowflake, Transact-SQL in SQL Server, and PL/SQL in Oracle Database (Google Cloud, 2026 ; The PostgreSQL Global Development Group, 2026 ; Snowflake Inc., 2026 ; Microsoft, 2026 ; Oracle, 2026a) .  \nHowever, current benchmarks for AI-assisted database development remain centered on either general-purpose programming or standalone declarative SQL. General code-generation benchmarks such as HumanEval, MBPP, MBPP+, and MultiPLE primarily evaluate programming in languages such as Python, Java, and C++ (Chen et al., 2021 ; Austin et al., 2021 ; Cassano et al., 2022 ; Liu et al., 2024) . Text-to-SQL benchmarks such as Spider, BIRD, and Spider 2.0 focus on generating standalone declarative queries over relational schemas (Yu et al., 2018 ; Li et al., 2023 ; Lei et al., 2025) . Even recent interactive database benchmarks such as Bird-Interact (Huo et al., 2025) remain centered on SQL querying rather than executable procedural database programs. As a result, the ability of AI systems to generate, modify, debug, and repair procedural database programs remains underexplored. To study this setting concretely, we introduce PLSQLBENCH, a benchmark for evaluating LLM systems on executable procedural database programming in PL/SQL. In this work, we focus on PL/SQL, an executable procedural SQL dialect with support for stored procedures, functions, packages, cursors and exceptions. Oracle Database is currently ranked first in the DB-Engines popularity ranking of database manageme","cbCaiarZ10i2t6TC","https://ap.wps.com/l/cbCaiarZ10i2t6TC","pdf",589114,24,"English","# Introduction\n## Benchmark Suite Overview\n## Contributions","[{\"question\":\"What does PLSQLBENCH measure for LLMs?\",\"answer\":\"PLSQLBENCH evaluates whether LLMs can generate executable PL/SQL programs whose correctness is verified through execution-based tests.\"},{\"question\":\"How is the benchmark structured in terms of tasks and interactions?\",\"answer\":\"The benchmark includes 2,594 single-turn tasks and 271 multi-turn conversations totaling 978 turns, requiring generation, modification, debugging, validation, and repair.\"},{\"question\":\"What difficulties do experiments reveal across LLMs?\",\"answer\":\"Experiments with eight LLMs show recurring problems with schema grounding, PL/SQL dialect fidelity, procedural control flow, exception handling, and consistency across conversation turns.\"}]","PLSQLBENCH - Benchmarking LLM Systems for Executable Procedural Database Programming | PDF"]