Expired50% confidenceBenchmarkExact time
An independent evaluation organization measured Opus 5.5 as ranking fourth among 60 models, with a score slightly lower than the previous generation.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
9/30/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/14/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedIn the Artificial Analysis composite index, Opus 5.5 scored 58, Sol scored 48, and Luna scored 37.74% similarUnverified在MATH数据集的Level 5竞赛级难题上，前沿模型准确率仍低于60%70% similarUnverifiedThe same model may rank very differently across different evaluation platforms.68% similarUnverifiedAnthropic states that Opus 5.5 is more than 30% faster than the previous generation and can save approximately 40% of compute under default settings.67% similarUnverifiedThe data shows that 'purely independent modes' occur in fewer than 5% of cases.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/961368API
curl https://kongchang.com/api/v1/knowledge/claims/961368MCP
get_claim(id=961368)