Repository hosting code to reproduce our paper (with Stanford, TogetherAI and Univ. Wisconsin-Madison), "DBPLANBENCH: Test-Time Optimization of Physical Query Plans with LLMs"
We assessed the ability of popular LLMs to generate accurate and efficient SQL from natural language prompts. Using a 200 million record dataset from the GH Archive uploaded to Tinybird, we asked the LLMs to generate SQL based on 50 prompts.