Unverified60% confidenceBenchmarkExact time

Early GPT-4 had a pass rate of only 1.7% on SWE-bench, Claude 3 Opus approximately 4.8%, and it was not until mid-2024 that the 20% mark was surpassed.

2

Sources

60%

Confidence

Long-term

Relevance

7/8/2026

First Seen

Sources

Claude Sonnet 5接入Devin：编程性能升级，配额消耗降低30%

rss6/30/2026

Related Claims

Unverified2024年以前主流模型在SWE-bench上的通过率普遍低于5%，Claude 3.5系列发布后跃升至49%（SWE-bench Verified子集）73% similar UnverifiedIn the correspondence rate with papers published after the model's cutoff date, DiscoveryRSI-27B reached 6.3%, GPT-6 was 2.5%, and Claude Opus 5 was 2.3%.73% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/212301

API

curl https://kongchang.com/api/v1/knowledge/claims/212301

MCP

get_claim(id=212301)