Verified65% confidenceFactTime unknown

Devin resolved 13.86% of real GitHub Issues in the SWE-bench test, surpassing the performance of Claude 2.

3

Sources

65%

Confidence

Long-term

Relevance

5/31/2026

First Seen

Sources

AI Coding Tools Deep Dive: How to Choose Between Qoder, Cursor, Windsurf, and Devin

bilibili烟岚九境

Related Entities

Devinproduct SWE-Benchconcept Claude 2model

Related Claims

Unverified在SWE-bench软件工程基准测试中，Claude 3.5系列的问题解决率显著高于同期竞品62% similar UnverifiedDevin once set the highest score of its time on the SWE-bench benchmark.59% similar UnverifiedClaude achieved a task completion rate of 14.9% on the OSWorld benchmark, representing the highest level at the time.58% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/3203

API

curl https://kongchang.com/api/v1/knowledge/claims/3203

MCP

get_claim(id=3203)