Internal evals: GPT 6.1 Sol beats Claude Opus 5.5 on knowledge work at 40% of the cost

emilahlback · x · 2026-09-30

Duplicate posting of the same eval claim: GPT 6.1 Sol topped the author's internal knowledge-work evals, completing more work independently than Claude Opus 5.5 at 40% of the cost and nearly twice the speed, leading in every industry measured.

Related event: GPT-6.1 Sol Launches with Astra-Level Intelligence at a Fifth of the Price(32 posts)→

Original post →

More from Models

Models channel →