Why we no longer evaluate SWE-bench Verified

2026-02-23来源 OpenAI BlogEnglish
SWE-bench Verified is increasingly contaminated and mismeasures frontier coding progress. Our analysis shows flawed tests and training leakage. We recommend SWE-bench Pro.

原文:https://www.a8q9.cn/en/article/why-we-no-longer-evaluate-swe-bench-verified-6beaae.html

相关文章