Unverified50% confidenceBenchmarkExact time
P99 latency on Fable 5.1 dropped from 6.6 seconds to 6.4 seconds, a limited long-tail improvement, because 30% of requests still call the model.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/19/2026
First Seen
Valid until: 1/17/2027
Sources
Related Entities
Related Claims
VerifiedP95表示95%的请求延迟低于该值，P99表示99%的请求延迟低于该值，高分位数指标专门捕捉尾部延迟严重程度78% similarUnverified基于规则的分类方案P99延迟通常在1毫秒以内，但难以处理语义歧义76% similarUnverifiedA good P50 median latency does not mean that P99 tail latency is acceptable; for real-time decision scenarios, tail latency is often the true bottleneck.76% similarUnverifiedThe model outputs only a risk level (such as RISK_LEVEL: 5) with no explanation; under a prompt of about 7000 tokens, Opus's P50 latency is about 1.5 seconds.73% similarUnverifiedP99 tail latency refers to the value corresponding to the 99th percentile after sorting all request response times from smallest to largest, and in Agent multi-turn session scenarios its impact on the stability of user experience is often greater than that of median TTFT.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1065408API
curl https://kongchang.com/api/v1/knowledge/claims/1065408MCP
get_claim(id=1065408)