# Xiaomi's MiMo-V2.6-Pro ends 34% of responses with a question

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

- Source: Artificial Analysis
- Published: 2026-11-05T16:30:00.000Z
- Bad Influence: https://badinfluence.news/items/jx3gjxm58w1zubyubgenjrrom
- Original: https://x.com/ArtificialAnlys/status/2118380321070539239

## Summary

In 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%.

## Post

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%)

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHWPmdDWXcAELEjm.jpg&mode=thumb&exp=1794096000&sig=5f0d8de6a790a569)