Cost Trade-offs of Reasoning and Non-Reasoning Large Language Models in Text-to-SQL

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Deochake, Saurabh, Mukhopadhyay, Debajyoti
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912950215770112
author Deochake, Saurabh
Mukhopadhyay, Debajyoti
author_facet Deochake, Saurabh
Mukhopadhyay, Debajyoti
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_22364
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Cost Trade-offs of Reasoning and Non-Reasoning Large Language Models in Text-to-SQL
Deochake, Saurabh
Mukhopadhyay, Debajyoti
Databases
Artificial Intelligence
Distributed, Parallel, and Cluster Computing
I.2.7; H.3.3; H.2.3
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.
title Cost Trade-offs of Reasoning and Non-Reasoning Large Language Models in Text-to-SQL
topic Databases
Artificial Intelligence
Distributed, Parallel, and Cluster Computing
I.2.7; H.3.3; H.2.3
url https://arxiv.org/abs/2512.22364