Skip to content

Xiaomi · Chat

MiMo V2.6 Pro

Xiaomi 🇨🇳ChatMiMo familyOpen weights. One of its sources says the weights are publicly available.
From Empiriolabs's listing:
Trillion-parameter flagship for agentic work, with native image, video, and audio understanding and reasoning across a 1M context.
llminfo IQ
136.7
Max context
1.1M
Listings
72

Evidence and sources

🤗 XiaomiMiMo/MiMo-V2.6-Pro-RLllminfo IQ 136.7, ranked among chat models. From 133 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 123.4, 95% interval 115–132. From 11 benchmark families across 5 sources. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.How Coding IQ is computedGood value (74.5). Cheaper per task than its benchmark results predict. From 35 benchmarks with measured task costs. Plenty of data behind it.How Value for money worksYap score: tokens used per coding task vs. models with the same resultsChatty (62 ±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. By effort: default 62 · none 57.Median 103,073 output tokens per task at default effort.How the Yap score worksReleased 21 Sep 2026Maker HQ: CN (according to Xiaomi's own website)
All rankings: #22 on NanoGPT recently #26 on OpenRouter this month #31 on OpenRouter today #37 on OpenRouter this weekSources: Xiaomi MiMo data, EmpirioLabs data, Models.dev data, llminfo researchPrimary data from Xiaomi MiMo from EmpirioLabs: primary mode, description from Models.dev: weights availability from llminfo research: release date

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ

Advantages

Open weights available

The weights are public. 4 of the 9 peers that say either way have open weights.

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 04:34 UTC.

Input & output

as stated by the model's providers
Text
Images
Audio
Video
Text

Capabilities

Supported operations and provider-stated features

VisionReasoningFunction callingStructured outputPrompt cachingWeb searchAudio input

Listings

 Xiaomimimo-v2.6-pro · fp8Sources: Models.dev data, Xiaomi MiMo data1M$0.435cache read $0.0036$0.87——
 Aihubmixxiaomi-mimo-v2.6-pro-free · freeSource: AIHubMix data docs1M$0.00$0.00——
 Neuralwattmimo-v2.6-pro-flex · flexSources: Models.dev data, NeuralWatt data1M$0.2828cache read $0.0023$0.5655——
 NanoGPTInference by NeuralwattRegions: 🇺🇸 USxiaomi/mimo-v2.6-pro · flexSource: NanoGPTNot published by the provider$0.2969cache read $0.0025$0.5938——
 GmicloudXiaomiMiMo/MiMo-V2.6-Pro · bf16Sources: GMI Cloud data, LiteLLM data1.1M$0.348cache read $0.0029$0.696——
 Avianxiaomi/mimo-v2.6-proSource: Avian.io Models data1M$0.3698cache read $0.0031$0.7395——
 Fastrouterxiaomi/mimo-v2.6-proSource: FastRouter data1M$0.387cache read $0.0032$0.783——
 OpenRouterInference by DeepInfraxiaomi/mimo-v2.6-pro · fp8Source: OpenRouter data docs1M$0.387cache read $0.0032$0.78371576ms
 FlowdotXiaomiMiMo/MiMo-V2.6-ProSource: FlowDot data1M$0.43$0.87——
 Kiloxiaomi/mimo-v2.6-proSources: Kilo AI Gateway data, Models.dev data1M$0.43cache read $0.0036$0.87——

5 listings without a price are hidden.

Included in plans

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Human preference

Arena ELO39 related benchmarks · 39 results

Agentic

Arena AgentSource: LMArena data
JobBenchSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Source: OpenRouter benchmark exports
21 Sep 2026 version · 90-day results
Across 6 providers lowest 76.3% median 77.4% highest 78.9%OpenRouter's automatic routing 76.8%
Show results from 6 providers and OpenRouter's automatic routingHide results from 6 providers and OpenRouter's automatic routing
  • Xiaomi
  • Novita
  • DeepInfra
  • StreamLake
  • PrimaLabs
  • OpenRouter's automatic routing
  • GMICloud

Coding

Arena ELOSource: LMArena data · Nov 2026
CyberGymSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
MiMoSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
ValsSource: Vals AI

Science

GPQA Diamond7 results
Source: OpenRouter benchmark exports
21 Sep 2026 version · 90-day results
Across 6 providers lowest 87% median 89.4% highest 90.6%OpenRouter's automatic routing 88.3%
Show results from 6 providers and OpenRouter's automatic routingHide results from 6 providers and OpenRouter's automatic routing
  • Novita
  • Xiaomi
  • StreamLake
  • DeepInfra
  • OpenRouter's automatic routing
  • GMICloud
  • PrimaLabs

Multilingual

EKI EstonianSource: Keelemudelite mõõdupuu data docs · Sep 2026

Reasoning

Instruction following

Math

General

OCR

Other

SuperCLUESource: SuperCLUE data
Vals16 related benchmarks · 18 results
Show 12 more resultsHide 12 results
Immigration
Source: Vals AI
MedCode
Source: Clinical Benchmarks data docs · Sep 2026
Setting not stated
Source: Vals AI
Setting not stated
MedScribe
Source: Clinical Benchmarks data docs · Sep 2026
Setting not stated
Source: Vals AI
Setting not stated
Router Index
Source: Vals AI
SAGE
Source: Vals AI
SRE Bench
Source: Vals AI

Data credits: Data by LLM Stats · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · LMArena, CC BY 4.0 (licence) · Baromètre de l’écriture IA, Johannes Eva; public numeric ranking data, © 2026 Johannes Eva, no results licence stated · Keelemudelite mõõdupuu: Independent LLM leaderboard for Estonian. Eesti Keele Instituut. https://moodupuu.eki.ee, CC BY 4.0. Latest per-benchmark results selected with partial-run flags retained. (licence) · OpenRouter public benchmark leaderboard and search-lane exports, CC BY 4.0. Fractional source scores converted to percentages; immutable dated snapshots. (licence) · Clinical Benchmarks (clinicalbenchmarks.ai), CC BY 4.0; fractions converted to percentages; source documents retain their own terms (licence) · Steel.dev Agent Leaderboards, MIT (licence)

Also known as: cline-pass/mimo-v2.6-pro, coding-xiaomi-mimo-v2.6-pro, deepinfra/mimo-v2.6-pro, empiriolabs/mimo-v2-6-pro, empiriolabs/mimo-v2-6-pro-ultraspeed, gmi/xiaomimimo/mimo-v2.6-pro, mimo-v2-6-pro, mimo-v2-6-pro-ultraspeed, mimo-v2.6-pro-flex, mimo-v2.6-pro-free, mimo-v2.6-pro-ultraspeed, opencode_go/mimo-v2.6-pro, streamlake/mimo-v2.6-pro, tencent/mimo-v2.6-pro, xiaomi-mimo-v2.6-pro-free, xiaomi/mimo-v2.6-pro, xiaomi/mimo-v2.6-pro-ultraspeed, xiaomi_mimo/mimo-v2.6-pro, xiaomimimo/mimo-v2.6-pro

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works