Verified65% confidenceFactExact time
SWE-bench由普林斯顿大学团队开发，Pro版本要求模型在真实GitHub代码仓库中定位Bug并生成修复补丁
3
Sources
65%
Confidence
Long-term
Relevance
7/13/2026
First Seen
Sources
GPT-5.6发布：三款模型对标Claude，ChatGPT Work超级应用全解析
bilibiliAI-seeker7/9/2026
Related Claims
Partially VerifiedSWE-Bench was developed by a Princeton University team and extracts tasks from real GitHub issues, requiring models to locate problems within complete codebases and generate fix patches84% similarVerifiedSWE-bench由普林斯顿大学提出，包含来自真实GitHub仓库的2294个软件工程问题84% similarVerifiedSWE-bench要求模型在真实GitHub仓库中定位并修复实际Issue84% similarVerifiedSWE-bench 由普林斯顿大学研究团队创建，从 GitHub 真实开源项目中抽取 issue，要求模型生成能通过测试用例的补丁84% similarUnverifiedSWE-bench Verified 由普林斯顿大学研究团队开发，从 GitHub 真实仓库抽取需修复的 Issue83% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/501555API
curl https://kongchang.com/api/v1/knowledge/claims/501555MCP
get_claim(id=501555)