OpenAI's GPT-6.1 Sol posts big agent benchmark gains at ~76% lower cost

OpenAIDevs · x · 2026-09-30

OpenAI's developer account shared new GPT-6.1 Sol agent benchmarks:

The headline story is cost efficiency: matching or beating the previous generation's max-effort scores at much lower reasoning settings.

Related event: OpenAI Launches GPT-6.1 Sol: Near-Astra Intelligence at One-Fifth the Price(27 posts)→

Original post →

More from Models

Models channel →