Verified75% confidenceFactTime unknown
SWE-bench Verified has been manually reviewed to ensure the quality and solvability of each instance
5
Sources
75%
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's scoring mechanism relies on an automated test suite; after a model submits a code patch, the system runs predefined unit tests to determine whether they pass78% similarVerifiedSWE-bench Verified is one of the authoritative industry leaderboards for AI programming ability, with human annotators filtering out samples with ambiguous descriptions or unstable tests.77% similarUnverifiedThe correctness of results containing a Lean 4 proof can be independently verified by anyone by running the Lean checker.73% 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% similarUnverifiedThe SAO team selected three high-difficulty benchmarks—SWE-Bench Verified, BeyondAIME, and IMOAnswerBench—for validation70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/26922API
curl https://kongchang.com/api/v1/knowledge/claims/26922MCP
get_claim(id=26922)