OpenAI Blog · Feb 23, 2026
Why we no longer evaluate SWE-bench Verified
Reviewed by Errol Vogt, Site support technician & online learning analyst · original summary · editorial policy
Why we no longer evaluate SWE-bench Verified. SWE-bench Verified is increasingly contaminated and mismeasures frontier coding progress. Our analysis shows flawed tests and training leakage. We recommend SWE-bench Pro. This update is relevant for small-office operators tracking changes in their tools.
Operator takeaway: For operators: review whether 'Why we no longer evaluate SWE-bench Verified' affects your current setup before relying on it in production.
ai