Jev performs really well in some evals for Executor Closest

@RhysSullivan Rhys · Sep 19, 2026 · case #635204 · listed via Jev Hub

Reported that Jev scored well on Executor evals, beat Gemma and vector search locally, and was cheap enough to ship despite data concerns.

The original post

Jev performs really well in some evals for Executor Closest local equivalent is Gemma & vector search but it’s worse and bloats the local app Figuring out what shipping it locally looks like - it’s cheap enough I’m happy to have the cost of it but is more about the data

Engagement when collected

Likes4

Bookmarks0

Reposts0

Replies0

Quotes0

Numbers are a snapshot taken from X when the case was added to the library (schema v1, collected 2026-09-19); they will not match today.

Where this case fits

Filed under classification & data extraction. In the pattern Jev is built for, the model answers a bounded question per step — and ordinary code acts on the answer, because the answer is already a value rather than a paragraph. Other posts in the same family are on the classification & data extraction page.

🗂️ Classification & data extraction