{"ID":2825075,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.22364","arxiv_id":"2512.22364","title":"Cost Trade-offs of Reasoning and Non-Reasoning Large Language Models in Text-to-SQL","abstract":"While Text-to-SQL systems achieve high accuracy, existing efficiency metrics like the Valid Efficiency Score prioritize execution time, a metric we show is fundamentally decoupled from consumption-based cloud billing. This paper evaluates cloud query execution cost trade-offs between reasoning and non-reasoning Large Language Models by performing 180 Text-to-SQL query executions across six LLMs on Google BigQuery using the 230 GB StackOverflow dataset. Our analysis reveals that reasoning models process 44.5% fewer bytes than non-reasoning counterparts while maintaining equivalent correctness at 96.7% to 100%, and that execution time correlates weakly with query cost at $r=0.16$, indicating that speed optimization does not imply cost efficiency. Non-reasoning models also exhibit extreme cost variance of up to 3.4$\\times$, producing outliers exceeding 36 GB per query, over 20$\\times$ the best model's 1.8 GB average, due to missing partition filters and inefficient joins. We identify these prevalent inefficiency patterns and provide deployment guidelines to mitigate financial risks in cost-sensitive enterprise environments.","short_abstract":"While Text-to-SQL systems achieve high accuracy, existing efficiency metrics like the Valid Efficiency Score prioritize execution time, a metric we show is fundamentally decoupled from consumption-based cloud billing. This paper evaluates cloud query execution cost trade-offs between reasoning and non-reasoning Large L...","url_abs":"https://arxiv.org/abs/2512.22364","url_pdf":"https://arxiv.org/pdf/2512.22364v2","authors":"[\"Saurabh Deochake\",\"Debajyoti Mukhopadhyay\"]","published":"2025-12-26T19:51:35Z","proceeding":"cs.DB","tasks":"[\"cs.DB\",\"cs.AI\",\"cs.DC\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}