Unverified80% confidenceFactTime unknown
Anthropic表示Sonnet 4.6在提示注入抵抗能力方面的表现与Opus 4.6相当
1
Sources
80%
Confidence
Medium-term (~90 days)
Relevance
5/31/2026
First Seen
Valid until: 8/29/2026
Sources
Claude Sonnet 4.6全面评测：性能逼近Opus的知识工作AI新标杆
bilibili英文白斑马
Related Entities
Related Claims
Unverified根据Anthropic发布的基准测试数据，Sonnet 4.5在编码能力上略优于Claude Opus 4.177% similarUnverifiedSonnet 4.6在'大海捞针'测试中的表现与Opus持平76% similarUnverifiedAnthropic可能直接跳过了Sonnet 4.7，从4.6直接升级到4.875% similarUnverifiedAnthropic在API中引入了effort参数，中等effort可匹配Sonnet 4.5的最佳SWE-Bench分数同时减少76%的输出token74% similarUnverifiedClaude Haiku 4.5的错误拒绝率低于Sonnet 4.5和Opus 4.1，是Anthropic迄今最安全的模型之一74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/7417API
curl https://kongchang.com/api/v1/knowledge/claims/7417MCP
get_claim(id=7417)