Enterprise evals: GPT-6.1 beats Opus 5.5 with 2x speed and 40% lower price

npew · x · 2026-09-30

Energy's Gabriel reports GPT 6.1 scores significantly higher than Opus 5.5 on internal enterprise evals measuring business intuition and computer use, with much higher completion rates, 40% lower price, and 2x the speed — the company has made it their default model. OpenAI's npew adds it's the best for real-world tasks.

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 →