Unverified50% confidenceFactTime unknown
SWE-Bench 的测试集来源于 Django、Flask、NumPy、Scikit-learn 等主流 Python 开源项目的真实 Bug 报告
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026
Sources
Claude 4.5 vs Gemini 3 Pro: A Comprehensive Coding Showdown
bilibiliClaudeEvangelist
Related Claims
UnverifiedSWE-bench 的评测任务来自 12 个主流 Python 开源仓库，包括 Django、Flask、scikit-learn 等84% similarPartially VerifiedSWE-bench收集的项目包括Django、scikit-learn、sympy等知名Python开源项目78% similarPartially VerifiedSWE-Bench测试集包含来自12个主流Python开源项目的2294个真实Bug修复任务77% similarUnverifiedSWE-bench 基准由普林斯顿大学 NLP 团队于 2023 年发布，从 12 个真实开源 Python 项目中抽取 2294 个经过验证的 Issue-PR 配对71% similarUnverifiedSWE-Bench contains 2,294 real bug-fix tasks from 12 mainstream Python open-source projects.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/55588API
curl https://kongchang.com/api/v1/knowledge/claims/55588MCP
get_claim(id=55588)