Unverified60% confidenceFactTime unknown

SWE-bench is a large language model programming capability evaluation benchmark introduced by a Princeton University research team in 2023, extracting 2,294 task instances from 12 mainstream Python open-source projects on GitHub.

2

Sources

60%

Confidence

Long-term

Relevance

6/1/2026

First Seen

Sources

Rovo Agent：每天2000万免费Token，SWE-bench排名第一的AI编程CLI工具

bilibiliAI-seeker

Related Entities

SWE-benchconcept Princeton Universitycompany

Related Claims

UnverifiedSWE-Bench由普林斯顿大学团队发布，从GitHub上12个真实Python开源项目抽取近2300个真实Issue，2024年初顶级模型通过率仅约4%-5%，至2025年头部模型已突破60%80% similar UnverifiedSWE-bench由普林斯顿大学团队提出，包含2294个来自Django、Flask、Scikit-learn等12个Python开源仓库的真实GitHub Issue-Pull Request对79% similar UnverifiedSWE-Bench was proposed by the Princeton NLP team in 2023, crawling 2,294 real Issue-PR pairs from GitHub and covering 12 mainstream Python projects.79% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/23479

API

curl https://kongchang.com/api/v1/knowledge/claims/23479

MCP

get_claim(id=23479)