End-to-End Text-to-SQL with Dataset Selection: Leveraging LLMs for Adaptive Query Generation

Benchmark Model Rank Results
text-to-sql-on-spiderEnd-to-end Text-to-SQL: Gpt-3.5-turbo–Execution Accuracy (Test): 91.44Exact Match Accuracy (Test): 60.45
text-to-sql-on-spiderEnd-to-end Text-to-SQL: Gpt-4o-mini–Execution Accuracy (Test): 92.44Exact Match Accuracy (Test): 64.78