Unverified90% confidenceFactTime unknown
SWE-bench Verified经过人工审核确保每个实例的质量和可解性
1
Sources
90%
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 Verified由人工标注者筛除描述模糊或测试不稳定的样本，是业界权威的AI编程能力排行榜之一77% similarUnverifiedSWE-Bench推出了SWE-Bench Verified和SWE-Bench Multimodal变体，前者人工筛选确保可解性，后者加入截图等多模态上下文72% similarUnverified该方案中 AI 自动评审会进行完整性检查、一致性检查和冗余检查等多维度验证71% similarVerifiedSWE-bench Verified是经过人工验证的子集，约500个样本，排除了描述模糊或测试不可靠的任务70% similarUnverified评估智能体编程能力的主流基准包括SWE-bench、SWE-bench Verified和HumanEval69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/26922API
curl https://kongchang.com/api/v1/knowledge/claims/26922MCP
get_claim(id=26922)