Unverified50% confidenceBenchmarkExact time
SWE-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
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/24/2026
First Seen
Valid until: 10/22/2026
Sources
Related Claims
UnverifiedSWE-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 review81% similarUnverifiedIn 2024, SWE-bench expanded its evaluation targets from functions to the fixing of real GitHub Issues.80% similarVerifiedSWE-bench requires models to locate and fix actual issues in real GitHub repositories.78% similarVerifiedSWE-bench was developed by a Princeton University team; the Pro version requires models to locate bugs and generate fix patches within real GitHub repositories.77% 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.75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/602782API
curl https://kongchang.com/api/v1/knowledge/claims/602782MCP
get_claim(id=602782)