Unverified50% confidenceFactExact time
Within certain parameter regions, averaging does not always reduce fluctuations, which differs from the intuition in convex optimization.
1
Sources
50%
Confidence
Long-term
Relevance
10/14/2026
First Seen
Sources
Related Entities
Related Claims
Unverified测试时计算扩展的边际收益并非线性，存在明显的收益递减区间74% similarUnverifiedModels at higher reasoning tiers such as Max or Ultra do not necessarily produce better or more efficient results, and sometimes benchmark scores actually decline due to over-reasoning74% similarUnverifiedImprovements in intelligence are often accompanied by nonlinear cost increases; upgrading from a mid-tier model to a top-tier model may raise benchmark scores by only a few percentage points, but calling costs can multiply several times over.73% similarUnverifiedThe expected value of a proper scoring rule is maximized only when the probability stated by the model is consistent with the true likelihood.72% similarUnverified模型的基准分数更高并不等于在所有场景下都更好用72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1023470API
curl https://kongchang.com/api/v1/knowledge/claims/1023470MCP
get_claim(id=1023470)