GPT-6 reportedly 'cooked' SRE-Bench: ~100% solve rate at pass@4, ~88% at pass@1

JiaweiLiu_ · x · 2026-09-04

Researcher Jiawei Liu (via @i2huer) reveals that a few weeks ago OpenAI told his team GPT-6 had basically "cooked" SRE-Bench, their software reverse-engineering benchmark — a nearly 100% solve rate at pass@4 and 88% at pass@1, at lower cost. It's a striking signal of GPT-6's generational leap in code understanding and reverse engineering.

Original post →

More from Models

Models channel →