Unverified60% confidenceBenchmarkExact time
The SWE-bench benchmark was released by a Princeton University research team in 2023 and contains 2,294 verified issue-fix commit pairs.
2
Sources
60%
Confidence
Long-term
Relevance
7/11/2026
First Seen
Sources
A Deep Dive into Cloud Coding Agents: How Users in China Can Choose Wisely
bilibili小行星AI观测站7/9/2026
Related Claims
UnverifiedSWE Bench由普林斯顿大学研究团队于2023年推出,测试集包含来自12个主流开源Python项目的2294个真实问题77% similarVerifiedSWE-bench is a software engineering capability evaluation benchmark introduced by a Princeton University research team in 2023.76% similarUnverifiedSWE-bench由普林斯顿大学Carlos E. Jimenez等研究者于2023年发布,包含来自12个真实Python开源仓库的2294个Issue-PR配对样本74% similarUnverifiedSWE-Bench由普林斯顿大学研究团队于2023年发布,要求模型在真实代码仓库语境下理解跨文件依赖、定位根因并生成补丁72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/485753API
curl https://kongchang.com/api/v1/knowledge/claims/485753MCP
get_claim(id=485753)