Get the latest tech news

A Jev that can ask Opus for help gives Opus accuracy at 4x lower cost


We tested Jev and GPT-6 Luna as judges for identity resolution. A hybrid of Jev and Claude Opus matched frontier accuracy at over 4x lower cost.

None

Get the Android app

Or read this on Hacker News

Read more on:

Photo of accuracy

accuracy

Photo of lower cost

lower cost

Photo of help

help

Related news:

News photo

Spotify is coming to United Airlines seatbacks — with help from Starlink

News photo

Claude Opus 5.5 Can Draw Permit-Level Architectural Drawings

News photo

HTTP/3 is faster with some work and help from Cloudflare