# How Snowflake uses Mistral

**2x** accuracy compared to single-shot SQL generation

As published on [mistral.ai](https://mistral.ai/customers/snowflake/), April 2026. Captured by usedby on 2026-10-09.

- Company: [Snowflake](https://www.usedby.ai/companies/snowflake.md)
- Tool: [Mistral](https://www.usedby.ai/tools/mistral.md)
- Industry: [Data & Analytics](https://www.usedby.ai/companies/industry/data-analytics.md)

## The use case: how Snowflake deploys Mistral

Snowflake uses Mistral Large and Codestral in Cortex Analyst, its AI assistant for structured data, to generate SQL from natural language questions and explain results conversationally. A multi-agent approach has several agents draft SQL and another synthesize the final query.

Summary written by usedby from the source page, in English. The figures are those of Mistral and Snowflake, not ours.

> 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 solution in the market.

- **14%**: “delivers approximately 14% higher accuracy than another competing text-to-SQL solution in the market”
- **90%**: “Cortex Analyst achieved ~90% or higher accuracy reliably across customer evaluations as well as in benchmark tests”

> With Mistral Large and Codestral, Snowflake is delivering cutting-edge text-to-sql capabilities for complex and nuanced enterprise data.
>
> Yusuf Ozuysal, Director of Engineering, Snowflake

Source: [mistral.ai](https://mistral.ai/customers/snowflake/), captured 2026-10-09.

## Other AI tools used by Snowflake

- [Fairmarkit](https://www.usedby.ai/tools/fairmarkit.md) — Confirmed
- [Yoodli](https://www.usedby.ai/tools/yoodli.md) — Confirmed
- [Zip](https://www.usedby.ai/tools/zip.md) — Confirmed
- [ZoomInfo](https://www.usedby.ai/tools/zoominfo.md) — Confirmed
- [6sense](https://www.usedby.ai/tools/6sense.md) — Observed
- [Apollo](https://www.usedby.ai/tools/apollo.md) — Observed

## Mistral users in Data & Analytics

- [BigDataCorp](https://www.usedby.ai/companies/bigdatacorp.md) — Confirmed
- [MongoDB](https://www.usedby.ai/companies/mongodb.md) — Observed

## What usedby checked

We compared the story with its live page on 2026-10-09.

- Checked: the figure 2x is on the page; its label is our wording.
- Checked: the passage quoted above is copied word for word from the page, near the name of Snowflake.
- Checked: the publication date is read from the page’s own metadata, never guessed.
- Checked: Snowflake uses Mistral. Confirmed line. Latest check across sources: 2026-10-15.
- Not checked: the result itself. We quote it; we did not measure it.

---
Source: https://www.usedby.ai/case-studies/snowflake-mistral · How we check: https://www.usedby.ai/methodology