Unverified50% confidenceBenchmarkExact time
SWE-Race is an AI programming benchmark targeting concurrency bugs, extracting 188 real concurrency defects from merged PRs across approximately 100 Python projects.
1
Sources
50%
Confidence
Long-term
Relevance
10/6/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedSWE-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.71% similarUnverifiedSkillCascade-Bench contains 213 validated cascading test cases covering multiple agent systems and application domains.67% similarUnverifiedOpenAI发布GeneBench Pro研究基准测试，包含129个评估任务，涵盖10个主要领域和21个细分方向，前沿模型最高得分31.5%67% similarUnverified突变测试通过对源代码进行小规模随机修改后运行现有测试套件，若测试未检测到突变体则说明测试覆盖存在盲区，主流工具包括 Java 的 PIT、Python 的 mutmut、JavaScript 的 Stryker67% similarVerifiedSWE-bench Verified is a human-verified subset of approximately 500 samples, excluding tasks with vague descriptions or unreliable tests.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/980429API
curl https://kongchang.com/api/v1/knowledge/claims/980429MCP
get_claim(id=980429)