AITOPAI热报
ModelsMulti-sourceSelected78°

Xiaomi releases MiMo-V2.6-Pro model

OpenRouter@OpenRouterAI
Post· 4 sources
View the post
Why we picked it

Available on OpenRouter, these models offer alternatives to agentic coding solutions from US companies like OpenAI and Anthropic.

Xiaomi launched MiMo-V2.6-Pro, a flagship model with over 1 trillion parameters. The company also introduced MiMo-V2.6-Flash, a smaller 309B MoE model with 15B active parameters. MiMo-V2.6-Pro-UltraSpeed offers the same Pro checkpoint at approximately 10x the output speed.

Image · OpenRouter
Original · OpenRouter

MiMo-V2.6-Pro: the 1T+ flagship, built for agentic coding and long-horizon work. MiMo-V2.6-Flash: smaller 309B MoE with 15B active. MiMo-V2.6-Pro-UltraSpeed: the same Pro checkpoint at ~10x the output speed. Browse all Xiaomi models: openrouter.ai/provider/xiaomi 💬 1 🔄 1 ❤️ 10 👀 1646 📊 2 ⚡

#MiMo-V2.6-Pro#MiMo-V2.6-Flash#Xiaomi#agentic coding#MoE

Keep reading

Recent stories with the same tag or section
PapersUS vs ChinaMulti-sourceSelected00:32
MiMo-V2.6-Pro Tops AA-PersonalityBench in Question-Ending Responses

Response-ending behaviour shapes how conversational and proactive an assistant feels, and this benchmark turns that personality trait into a measurable signal. Product teams choosing a model for customer-facing chatbots can use these figures to match tone, since a 34% question rate reads very differently from a 0.1% one. The spread between MiMo-V2.6-Pro and DeepSeek V4.1 Flash also shows two Chinese labs optimising for opposite interaction styles.

#MiMo-V2.6-Pro#DeepSeek#GPT-6#AA-PersonalityBench
Event
官方账号Artificial Analysis@ArtificialAnlys11 sourcesSource
ModelsUS vs ChinaMulti-sourceSelected04:15
Artificial Analysis launches leaderboard for Cognition's FrontierCode 1.1

The benchmark's merge-focused grading penalises the messy diffs and unhelpful tests that cheaper evaluations ignore, so leaderboard gaps here reflect real maintainer acceptance rather than raw test-passing. Leading models still fail over 40% of tasks, and nine tasks went unsolved by every model evaluated. Teams choosing coding agents can weigh GPT-6.1 Sol's 49% score at US$0.81 per task against Claude Opus 5.5's 52% at far higher cost, with open-weights options like MiMo-V2.6-Pro at 45% close behind.

#FrontierCode#Cognition#Claude Opus 5.5#GPT-6.1 Sol
Event
官方账号Artificial Analysis@ArtificialAnlys11 sourcesSource