Unverified50% confidenceFactExact time
When the 95% confidence intervals of two models overlap, the ranking difference between them may not be statistically meaningful.
1
Sources
50%
Confidence
Long-term
Relevance
9/6/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedIn scenarios with extreme class imbalance, even an accuracy as high as 95% may indicate that the model is completely unable to identify the minority class.76% similarUnverifiedIn the Elo rating system, when the score difference between two models is within 30–50 points, they are generally considered to be at a statistically indistinguishable level.70% similarUnverifiedMcNemar 检验关注两个模型在每个样本上的分歧情况，只有判断结果不一致的样本（b和c单元格）具有信息量，两者都对或都错的样本被视为无关信息67% similarUnverified模型的基准分数更高并不等于在所有场景下都更好用67% similarUnverified当综合评估指数中顶尖模型得分接近天花板时会出现基准饱和问题，60分对59分的差距在统计学上通常处于误差范围之内65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/863345API
curl https://kongchang.com/api/v1/knowledge/claims/863345MCP
get_claim(id=863345)