Unverified50% confidenceFactExact time

SWE-bench评估基准收集了来自真实GitHub仓库的数百个Issue和对应的修复方案

1

Sources

50%

Confidence

Medium-term (~90 days)

Relevance

7/2/2026

First Seen

Valid until: 9/30/2026

Sources

OpenAI Codex深度解析：从ChatGPT到AI编程智能体的跨越

bilibili饭饭大王ouo6/23/2026

Related Claims

UnverifiedSWE-bench Verified 由普林斯顿大学研究团队开发，从 GitHub 真实仓库抽取需修复的 Issue79% similar VerifiedSWE-bench要求模型在真实GitHub仓库中定位并修复实际Issue76% similar VerifiedSWE-bench（真实GitHub Issue修复率）被业界视为衡量编程Agent能力最具参考价值的指标76% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/42128

API

curl https://kongchang.com/api/v1/knowledge/claims/42128

MCP

get_claim(id=42128)