Unverified50% confidenceFactExact time
Text Arena使用Bradley-Terry模型作为底层概率框架，模型A获胜的预期概率为1/(1+10^((Rb-Ra)/400))
1
Sources
50%
Confidence
Long-term
Relevance
8/7/2026
First Seen
Sources
阿里通义冲上Text Arena第二名，Qwen模型实力解析
Related Claims
Unverified在Elo系统中，若模型A评分为Ra、模型B评分为Rb，A获胜的期望概率为1/(1+10^((Rb-Ra)/400))74% similarUnverified在8个模型均随机猜测的假设下，单次二元预测中至少有一个押中的概率约99.6%63% similarUnverifiedIn the Elo system, a rating difference of 400 points means the stronger player's expected win rate is approximately 91%, with player A's winning probability being 1/(1+10^((Rb-Ra)/400)).62% similarUnverified在二维高斯分布下，1-σ椭圆包含真实状态概率约39.4%，2-σ约86.5%，3-σ约98.9%61% similarUnverified期望价值的计算方式为各种可能结果的收益乘以其发生概率之和60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/700717API
curl https://kongchang.com/api/v1/knowledge/claims/700717MCP
get_claim(id=700717)