Unverified50% confidenceBenchmarkExact time
Online A/B testing showed a 5% decrease in skip rate.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/28/2026
First Seen
Valid until: 12/27/2026
Sources
Related Entities
Related Claims
UnverifiedLiveNerf's criterion is: if Opus 5.5's score deviates by more than 7.5 points, it is treated as a potential signal of capability degradation.68% similarUnverifiedAn early iteration scored five percentage points lower than the Huihui base model on the IFEval instruction-following benchmark.68% similarUnverified研究表明将收入从精确值泛化为5个区间可能导致模型AUC下降2-5个百分点68% similarUnverified4-bit quantization compared to FP16 typically results in a 0.5–2% drop in benchmark accuracy.68% similarUnverifiedIn real-environment A/B testing, the post-trained checkpoint reduced the tool-call failure rate by 21.2% relatively compared to the earlier version.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/955681API
curl https://kongchang.com/api/v1/knowledge/claims/955681MCP
get_claim(id=955681)