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.

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 knowSQRL-35B-A3B: 70.6% execution accuracy on BIRD Dev benchmark
Outperforms Claude Opus 4.6 on BIRD Dev
Distills to self-hostable 4B and 9B checkpoints
Novel architecture: read-only database inspection before query commit
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.