Snowflake achieves 2x greater accuracy with text-to-SQL using Mistral models
Based on internal evaluation sets, using Mistral Large and Codestral, Cortex Analyst is consistently close to 2x more accurate than single-shot SQL generation from state-of-the-art LLMs and delivers approximately 14% higher accuracy than another competing text-to-SQL Beyond basic queries: Achieving 2x greater accuracy with text-to-sql on Snowflake. Snowflake turned to two Mistral models as potential answers: Codestral , an open-weight model explicitly tailored for code generation tasks, and Mistral Large , for reasoning, language generation, and code generation.
- Agent or tool
- Snowflake Cortex
- Topic
- Software Development
- Reported on
- Case study (Mistral)
- Added
- 2026-11-12
Why it matters
Coding agents are moving from autocomplete to doing whole tasks: reading a codebase, making a plan and changing many files. This case is a concrete example of where that works in practice. It is one of 221 sightings filed under Software Development on Agent Sightings (number 27 by interest), and one of 7 involving Snowflake Cortex.
How you could try it
Here is a reusable prompt, written by us in our own words, that captures the task. Paste it into Snowflake Cortex or any similar agent and adjust the details to your situation.
I want a coding agent to plan first, work on a branch, and show me the diff before anything is merged. The tool in the source case was Snowflake Cortex.
Tip: Work on a fresh branch, ask for a plan before edits, and review the diff and test results before merging.
Source
Read the original first-hand account on Case study (Mistral): https://mistral.ai/customers/snowflake. Our summary is a paraphrase; details are in the source.
Featured in these guides
Built an AI agent? Feature your agent on Agent Sightings, free submission or a featured spot.
Browse more like this
Related sightings
- Snowflake Cortex AI
- A contractor's personal Claude Code agent allegedly ran inside a secure Pentagon system for two months
- Claude Code's 3-word status line reportedly burns 15 to 20% of tokens
- Rocket Money on building agents that fix their own code
- ActiveCampaign Deflects More than 60% of Chat Tickets and Launches a Full AI Program with Forethought
- Novo Transforms Patient Care With Agentic AI