Expired80% confidenceFactTime unknown
Anthropic stated that Sonnet 4.6 performs on par with Opus 4.6 in terms of resistance to prompt injection.
1
Sources
80%
Confidence
Medium-term (~90 days)
Relevance
5/31/2026
First Seen
Valid until: 8/29/2026(expired)
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
UnverifiedAccording to benchmark data released by Anthropic, Sonnet 4.5 is slightly superior to Claude Opus 4.1 in coding capability.77% similarUnverifiedSonnet 4.6 performs on par with Opus on the 'needle-in-a-haystack' test.76% similarUnverifiedAnthropic可能直接跳过了Sonnet 4.7，从4.6直接升级到4.875% similarUnverifiedAnthropic introduced an effort parameter in the API, where medium effort can match Sonnet 4.5's best SWE-Bench score while reducing output tokens by 76%.74% similarUnverifiedClaude Haiku 4.5 has a lower false refusal rate than Sonnet 4.5 and Opus 4.1, making it one of the safest models Anthropic has released to date.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)