AITOPAI热报
ModelsMulti-sourceSelected73°

Xiaomi MiMo-V2.6-Pro debuts as top open weights model on Artificial Analysis index

elvis@omarsar0
Post· 6 sources
View the post
Why we picked it

At US$0.435 per 1M input tokens, MiMo-V2.6-Pro undercuts most frontier closed models, and open weights let teams in cost-sensitive Southeast Asian markets self-host or deploy via API.

Xiaomi released MiMo-V2.6-Pro as an open weights model, scoring 46 on the Artificial Analysis Intelligence Index, up from 26 for MiMo-V2.5-Pro. At US$0.13 per Intelligence Index task, it sits on the Intelligence vs. Cost per Task Pareto frontier. Pricing stays at US$0.435 per 1M input tokens with a 99% cache-hit discount and US$0.87 per 1M output tokens. The model is an MoE with 1.02T total parameters and 42B active parameters. Xiaomi is also open-sourcing MiMo-V2.6-Flash, MiMo-V2.6-Distill-Qwen-9B, a technical report, 7K+ RL task environments and an end-to-end RL framework.

Original · elvis

New open frontier model! MiMo-V2.6 Pro lands on the Intelligence-vs.-Cost-per-Task Pareto frontier. The best part is that they are open-sourcing Pro and Flash, MiMo-V2.6-Distill-Qwen-9B, the technical report, 7K+ RL task environments, an end-to-end RL framework, and composable mini-harnesses. Artificial Analysis @ArtificialAnlys MiMo-V2.6-Pro debuts as the top open weights model on the Artificial Analysis Intelligence Index (46). At $0.13 per Intelligence Index task, it lands on the Intelligence vs. Cost per Task Pareto frontier @Xiaomi has just released MiMo-V2.6-Pro, an open weights model with major advances in intelligence over its predecessor, MiMo-V2.5-Pro (Intelligence Index: 26). Despite the improvement, it retains the same attractive pricing at $0.435 per 1M input tokens (with a 99% cache-hit discount) and $0.87 per 1M output tokens. This makes MiMo-V2.6-Pro one of the most cost-efficient models to deploy. MiMo-V2.6-Pro is an MoE model with 1.02T total parameters and 42B active parameters. Stay tuned for additional analysis of the model. Check out MiMo-V2.6-Pro full benchmarking breakdown here: artificialanalysis.ai 🔗 View Quoted Tweet 💬 5 🔄 1 ❤️ 15 👀 3146 📊 5 ⚡

  • Clement Delangue09-21 21:03原文
  • Paul Couvert09-21 21:04原文
  • Artificial Analysis09-23 18:54原文
  • Latent Space (swyx)09-22 06:30原文
  • Decoder09-22 11:42原文
#MiMo-V2.6-Pro#Xiaomi#open-source models#Artificial Analysis Intelligence Index

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