Unverified60% confidenceFactExact time
SWE-bench Verified was launched by Princeton University in 2023 to measure AI's automated software engineering capability on real GitHub Issues, with its Verified subset having undergone human review
2
Sources
60%
Confidence
Long-term
Relevance
7/22/2026
First Seen
Sources
Related Claims
UnverifiedSWE-bench要求模型修复GitHub上真实Issue，SWE-bench Verified版本于2024年兴起并成为衡量AI Agent编程能力的黄金标准81% similarVerifiedSWE-Bench was introduced by Princeton University in 2023 and evaluates AI programming ability by drawing thousands of resolved issues from real open-source projects on GitHub.78% similarVerifiedSWE-bench Verified was developed by a Princeton University research team and draws issues requiring fixes from real GitHub repositories.76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/594003API
curl https://kongchang.com/api/v1/knowledge/claims/594003MCP
get_claim(id=594003)