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.
More from Models
- GPT-6 Astra reportedly scores 100% on ExploitBench, finds two zero-days in testing — VraserX · 2026-09-04
- AI launch playbook under fire: influencer hype chorus vs paying users locked out — xeophon · 2026-09-04
- Team finetunes Gemma 12B for audio proofreading, benchmarks it against Gemini — ojasvi_yadav · 2026-09-04
- First impressions of Astra: clean tone and zero jargon in its writing — soumitrashukla9 · 2026-09-04
- Nadella says early customers already use Astra on Azure as Altman responds — i_dg23 · 2026-09-04
- Abu Dhabi institute IFM releases 6 fully open-source AI models with data, code & methods — Polymarket · 2026-09-04