Verified85% confidenceFactTime unknown
SWE-bench直接从GitHub真实开源项目中提取issue和对应的pull request，要求AI系统理解问题描述、定位代码缺陷并生成正确的修复补丁
5
Sources
85%
Confidence
Long-term
Relevance
6/1/2026
First Seen
Sources
SWE-bench官方博客上线：AI编程评测标准进入新阶段
twitterSWEbench
Related Entities
Related Claims
UnverifiedSWE-bench从真实GitHub Issues中提取任务，要求模型修复主流开源项目的真实Bug，被视为衡量实际解决工程问题能力的黄金标准84% similarPartially 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 patches80% similarUnverifiedSWE-bench从主流Python开源项目提取真实GitHub Issue，要求模型生成能通过官方测试套件的代码补丁80% similarVerifiedSWE-bench直接使用真实的GitHub Issue作为测试题目，要求模型在完整代码仓库中定位并修复Bug80% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/26919API
curl https://kongchang.com/api/v1/knowledge/claims/26919MCP
get_claim(id=26919)