Unverified80% confidenceFactTime unknown
Sonnet 4.6在'大海捞针'测试中的表现与Opus持平
1
Sources
80%
Confidence
Medium-term (~90 days)
Relevance
5/31/2026
First Seen
Valid until: 8/29/2026
Sources
Claude Sonnet 4.6评测:十分之一价格实现旗舰级AI性能
bilibili乱砍一通
Related Entities
Related Claims
Unverified测试选择Claude Sonnet 4.6而非Opus 4.7作为基准线,理由是Opus太强没有对比意义77% similarUnverifiedAnthropic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76% similarUnverifiedSonnet 4.6与Opus 4.6相比,在大多数基准测试中表现几乎持平,但推理速度更快、调用成本更低74% similarUnverifiedSonnet 4.6在OS World Verified基准测试中得分72.5%72% similarUnverifiedClaude Sonnet 4.6在GDPVal AA基准测试中得分超过了Opus 4.671% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/13723API
curl https://kongchang.com/api/v1/knowledge/claims/13723MCP
get_claim(id=13723)