SWE-bench Verified
基准测试
能力
Real GitHub issues, real repos — the coding-agent standard.
您正在查看一条基准测试记录：这是业界用于衡量芯片或模型的测试——以及它实际告诉你什么。
SWE-bench gives a model an actual repository and issue; success means a patch that passes the tests. The Verified subset (human-validated, with OpenAI) became the metric coding agents live by — from single digits in 2023 to ~80% at the 2025 frontier — and the number behind every 'AI software engineer' claim.
它如何与整个技术栈相连
本记录的关联链接一览——点击分组可直接跳转。
基准测试
来源
记录审阅截至 2026-01-15 — 查看 方法论.