Cost Trade-offs of Reasoning and Non-Reasoning Large Language Models in Text-to-SQL
On the map: LLM reasoning → Knowledge- and tool-augmented reasoning
Abstract (arXiv)
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×, producing outliers exceeding 36 GB per query, over 20× 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.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 18 of its 29 references that are in the map. First posted on arXiv 26 Dec 2025.
Builds on
18 of 29 references.
Closest ancestors · 2
Same direction, newest first
- 2025Think2SQL: Reinforce LLM Reasoning Capabilities for Text2SQL21 Apr
- 2024CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL2 Oct
Other references · 16
- 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
- 2017Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learningcited by 679
- 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 667
- 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 465
- 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 378
- 2024Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflowscited by 223
- 2024CodeS: Towards Building Open-source Language Models for Text-to-SQLcited by 183
- 2023MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQLcited by 158
- 2019Neo: A Learned Query Optimizercited by 80
- 2025SQL-R1: Training Natural Language to SQL Reasoning Model By Reinforcement Learningcited by 67
- 2019An End-to-End Learning-based Cost Estimatorcited by 43
- 2025XiYan-SQL: A Novel Multi-Generator Framework For Text-to-SQLcited by 40
4 more
- 2024LLM-R2: A Large Language Model Enhanced Rule-based Rewrite System for Boosting Query Efficiencycited by 16
- 2024Towards Optimizing SQL Generation via LLM Routingcited by 5
- 2024ABACUS: A FinOps Service for Cloud Cost Optimizationcited by 4
- 2022BigBird: Big Data Storage and Analytics at Scale in Hybrid Cloudcited by 3
Built on by
Citing papers per year: 2026: 2.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2025Cheaper, Better, Faster, Stronger: Robust Text-to-SQL without Chain-of-Thought or Fine-Tuning
- 2026Are LLM-Based Retrievers Worth Their Cost? An Empirical Study of Efficiency, Robustness, and Reasoning Overhead
- 2024Lucy: Think and Reason to Solve Text-to-SQL
- 2026Optimizing Small Language Models for NL2SQL via Chain-of-Thought Fine-Tuning
- 2025Economic Evaluation of LLMs
- 2025SQLForge: Synthesizing Reliable and Diverse Data to Enhance Text-to-SQL Reasoning in LLMs
- 2026100x Cost & Latency Reduction: Performance Analysis of AI Query Approximation using Lightweight Proxy Models
- 2026Both Ends Count! Just How Good are LLM Agents at "Text-to-Big SQL"?