Partially Verified80% confidenceFactTime unknown
The SWE-Bench test set contains 2,294 real bug-fix tasks from 12 mainstream Python open-source projects.
7
Sources
80%
Confidence
Long-term
Relevance
5/31/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedSWE-bench collected 2,294 GitHub Issues and their corresponding fix patches from 12 real Python open-source projects including Django, scikit-learn, and sympy.78% similarVerifiedThe SWE-bench benchmark was released in 2023 by Princeton University's NLP team, extracting 2,294 validated Issue-PR pairs from 12 real-world open-source Python projects.70% similarUnverifiedWhen ChatGPT built a Python CLI to-do app, 1 of the 8 unittest tests it first generated failed, because the test called add_task but captured the output of list_tasks.69% similarUnverifiedSWE-bench 的评测任务来自 12 个主流 Python 开源仓库，包括 Django、Flask、scikit-learn 等68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/3035API
curl https://kongchang.com/api/v1/knowledge/claims/3035MCP
get_claim(id=3035)