Verified65% confidenceBenchmarkExact time
Claude Sonnet 5 在 SWE-bench Verified(Agentic Coding)上得分 63.22%,距 Opus 4.8 约差 6 个百分点
3
Sources
65%
Confidence
Medium-term (~90 days)
Relevance
7/12/2026
First Seen
Valid until: 10/10/2026
Sources
Claude Sonnet 5深度实测:性能亮眼但定价策略暗藏玄机
bilibiliNixAI6/30/2026
Related Claims
UnverifiedClaude Sonnet 4.6在GDPVal AA基准测试中得分超过了Opus 4.681% similarVerifiedClaude 3.7 Sonnet在SWE-bench Verified基准测试中得分超过60%81% similarUnverifiedClaude Sonnet 4.6在智能体终端编码基准测试中从51%提升至59%78% similarUnverifiedSonnet 5 的 Intelligence Index 比 Sonnet 4.6 高出 6 分,在代理知识工作任务上超过了 Opus 4.876% similarUnverifiedClaude Sonnet 4.6在OS World(智能体计算机使用)测试中从61.4%提升至72.5%76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/491482API
curl https://kongchang.com/api/v1/knowledge/claims/491482MCP
get_claim(id=491482)