GPT-6.1 Sol hits 75.2% on DeepSWE v1.1 at ~76% lower per-task cost

OpenAIDevs · x · 2026-09-30

In a follow-up to its benchmark thread, OpenAI's developer account reports GPT-6.1 Sol scores 75.2% on DeepSWE v1.1 at high reasoning effort, surpassing GPT-6 Sol's best of 68.8% at maximum effort, with roughly 76% lower cost per task.

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 →