Preprint
Aug 2026
PLSQLBench: Benchmarking LLM Systems for Executable Procedural Database Programming
PLSQLBench is the first benchmark for evaluating whether LLMs can write executable PL/SQL programs, with correctness measured through execution-based tests, and recurring difficulties in schema grounding, PL/SQL dialect fidelity, procedural control flow, exception handling, and cross-turn consistency are revealed.
Marianne Menglin Liu, Leonid Boytsov, Daniel W. Peterson et al.
· 0 citations