创建

登录 ReadmeX

或

了解我们如何处理你的信息: 隐私政策

ReadmeX

陪你读懂 AI 动态

今天,想先了解什么?

选一份动态总结,或直接聊聊你的问题。

社区和关注动态总结只属于你自己。

资讯

MiMo-V2.6-Pro问句结尾比例居首

AI 总结

Artificial Analysis 的测量显示,MiMo-V2.6-Pro 有 34% 的 AA-PersonalityBench 回复以问题结尾,在受测模型中占比最高。GPT-6 Astra 以 32% 位居其后,GPT-6.1 Sol、Muse Glimmer 和 Muse Spark Open 的占比分别为 29%、28% 和 26%。

深度见解

这项独立测量结果为比较 AA-PersonalityBench 中各模型的人格与回复风格提供了新的参考。

In AA-PersonalityBench, MiMo-V2.6-Pro ends 34% of its responses with a question, the highest share of any model measured

The share of responses that end with a question ranges from 34% down to 0% across the models measured. Six models end fewer than 0.5% of their responses with a question.

Share of responses that end with a question:

➤ Most often: MiMo-V2.6-Pro (34%), GPT-6 Astra (32%), GPT-6.1 Sol (29%), Muse Glimmer (28%) and Muse Spark Open (26%)

➤ Least often: GPT-5.4 mini (0.0%), Nemotron 3 Ultra (0.0%), DeepSeek V4.1 Flash (0.1%), DeepSeek V4.1 Flash 1017 (0.1%), GPT-3.5 Turbo (0.2%) and Grok 4.7 (0.4%)

#MiMo-V2.6-Pro#AA-PersonalityBench#Artificial Analysis#GPT-6 Astra#GPT-6.1 Sol#Muse Glimmer#Muse Spark Open#GPT-5.4 mini#Nemotron 3 Ultra#DeepSeek V4.1 Flash#GPT-3.5 Turbo#Grok 4.7

原文约 1 分钟读完阅读原文
群聊

还没有评论,来说说你的看法。