Artificial Analysis reports MiMo-V2.6-Pro ends most responses with a question
Overview
Artificial Analysis reports that Xiaomi's MiMo-V2.6-Pro ends 34% of its responses with a question in AA-PersonalityBench, the highest share of any model it measured.
GPT-6 Astra follows at 32% and GPT-6.1 Sol at 29%. Six models, including GPT-5.4 mini and Nemotron 3 Ultra, end under 0.5% of responses with a question.
Written by AI from the articles below · updated Nov 5, 11:31 AM ET
Check the sources:
Article timeline
The articles in this story. Times are ET.
Artificial Analysis@ArtificialAnlysOfficialXiaomi's MiMo-V2.6-Pro ends 34% of responses with a questionAIIn Artificial Analysis's AA-PersonalityBench, Xiaomi's MiMo-V2.6-Pro ends 34% of its responses with a question, the highest share of any model measured. GPT-6 Astra follows at 32%, and GPT-6.1 Sol at 29%, while six models including GPT-5.4 mini and Nemotron 3 Ultra end under 0.5%.

Heat Trend
Not enough continuous observations to show a trend yet.