FrontierThe story, in brief

Feyn AI Releases SQRL, a Text-to-SQL Model Family That Inspects the Database Before Writing a Query

70.6% execution accuracy. Feyn AI's SQRL just beat Claude Opus on text-to-SQL — and distills to 4B parameters.

Illustration of a transparent lens revealing connected networks across layers of paper.
Exploring the next frontier of AI research.AI illustration by KeyNews
The KeyNews take

Why it matters

Feyn Labs demonstrated a novel architectural approach (database inspection before query generation) that achieves competitive performance with smaller, self-hostable models. This matters because it shows an alternative path to expensive closed-model APIs for enterprise database query tasks.

The key facts

5 to know
  1. SQRL-35B-A3B: 70.6% execution accuracy on BIRD Dev benchmark

  2. Outperforms Claude Opus 4.6 on BIRD Dev

  3. Distills to self-hostable 4B and 9B checkpoints

  4. Novel architecture: read-only database inspection before query commit

  5. Text-to-SQL model family release

Go to the source

MarkTechPostmarktechpost.com

Publisher excerpt: Feyn Labs has released SQRL, a family of text-to-SQL models that inspect a database with read-only probes before committing to a query. The flagship SQRL-35B-A3B reports 70.6% execution accuracy on BIRD Dev, edging Claude Opus 4.6, and distills into self-hostable 4B and 9B checkpoints.
Read original report
Back to today's editionMore frontier news

Keep reading

Related stories

More from Frontier