Skip to content

Xiaomi · Chat

MiMo V2.5

Xiaomi 🇨🇳ChatMiMo familyOpen weights. One of its sources says the weights are publicly available.
From Neosantara's listing:
MiMo-V2.5 is a native omnimodal model by Xiaomi delivering flagship-level agentic performance at roughly half the inference cost. With a 1M token context window, it handles text, image, and video input for agent workflows that need strong reasoning, rich perception, and cost efficiency.
llminfo IQ
127.0
Maker's price
$0.175 blended / 1M
Max context
1.1M
Listings
38

Evidence and sources

🤗 XiaomiMiMo/MiMo-V2.5311B params Model architecture, as its sources state it llminfo IQ 127.0, ranked among chat models. From 145 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 107.8, 95% interval 102–114. From 12 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 (59.9). Cheaper per task than its benchmark results predict. From 27 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 resultsTypical (55 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.Median 18,431 output tokens per task at default effort.How the Yap score worksReleased 27 Apr 2026Maker HQ: CN (according to Xiaomi's own website)
All rankings: #107 on NanoGPT recently #145 on OpenRouter today #167 on OpenRouter this week #174 on OpenRouter this monthSources: LMArena data, Models.dev data, AI/ML API data, Morpheus Inference Marketplace data, Neosantara Inference data, Hugging FacePrimary data from LMArena from Models.dev: name, weights availability from AI/ML API: primary mode from Morpheus Inference Marketplace: architecture, parameter count from Neosantara Inference: description from Hugging Face: release date

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ
We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 06:07 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 9 maker's prices; 1 market median price.

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-v2.5 · fp8Source: Models.dev data1M$0.14cache read $0.0028$0.28
 Aihubmixaihubmix/coding-xiaomi-mimo-v2.5 · codingSource: LiteLLM data1M$0.08cache read $0.0016$0.16
 Gmicloudgmi/XiaomiMiMo/MiMo-V2.5 · fp8Source: LiteLLM data1.1M$0.119cache read $0.0024$0.238
 Atlascloudxiaomi/mimo-v2.5Source: AtlasCloud data1M$0.14cache read $0.0028$0.28
 Cometapimimo-v2.5Source: CometAPI Pricing dataNot published by the provider$0.14$0.28
 Hugging FaceInference by DeepInfraXiaomiMiMo/MiMo-V2.5Source: Hugging Face Inference Providers data262K$0.14$0.28
 MeganovaXiaomiMiMo/MiMo-V2.5Source: MegaNova data1M$0.14$0.28
 Cline Passcline-pass/mimo-v2.5Source: Models.dev data1M$0.14cache read $0.0028$0.28
 Impossiblxiaomi/mimo-v2.5Source: Models.dev data1M$0.14cache read $0.003$0.28
 Llmtrmimo/mimo-v2.5Source: Models.dev data1M$0.14$0.28
Show all 34 listings

Showing 10 of 34: the maker's own listing first, then the cheapest per 1M input tokens from each provider.

Also sold by Adzuki, Aimlapi, DeepInfra, Ionet, Kilo, NanoGPT, Neosantara, Nous Portal, Novita AI, Opencode Go, Openroute Cn, OpenRouter, Requesty, Standardcompute, Venice, Zenmux.

4 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 ELO60 related benchmarks · 60 results
Source: LMArena data · Nov 2026
BenchmarkScore
Arena ELO
Chinese
Creative Writing
English
Show 56 more benchmarksHide 56 benchmarks
BenchmarkScore
Exclude Ties
Expert
French
German
Hard Prompts
Hard Prompts English
Industry Business and Management and Financial Operations
Industry Entertainment and Sports and Media
Industry Life and Physical and Social Science
Industry Mathematical
Industry Medicine and Healthcare
Industry Software and It Services
Industry Writing and Literature and Language
Japanese
Korean
Longer Query
Multi Turn
Non English
Polish
Russian
Spanish
Style-Controlled
Text Factuality
Text Factuality - Chinese
Text Factuality - Creative Writing
Text Factuality - English
Text Factuality - Exclude Ties
Text Factuality - Expert
Text Factuality - French
Text Factuality - Hard Prompts
Text Factuality - Hard Prompts English
Text Factuality - Industry Business and Management and Financial Operations
Text Factuality - Industry Entertainment and Sports and Media
Text Factuality - Industry Life and Physical and Social Science
Text Factuality - Industry Mathematical
Text Factuality - Industry Medicine and Healthcare
Text Factuality - Industry Software and It Services
Text Factuality - Industry Writing and Literature and Language
Text Factuality - Japanese
Text Factuality - Korean
Text Factuality - Longer Query
Text Factuality - Multi Turn
Text Factuality - Non English
Text Factuality - Russian
Text Factuality - Spanish
Vision
Vision - Chinese
Vision - Creative Writing Vision
Vision - Diagram
Vision - English
Vision - Entity Recognition
Vision - Homework
Vision - Humor
Vision Style-Controlled
Design Arena EloSource: Design Arena Leaderboards data · Nov 2026

Coding

Arena ELOSource: LMArena data · Nov 2026
Claw-EvalSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Reported by Xiaomi MiMo · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Xiaomi MiMo-V2.5 official release/model card · Xiaomi internal coding-agent evaluation
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
ValsSource: Vals AI

Long context

Agentic

SWE-Bench Pro2 results
Reported by Xiaomi MiMo · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Xiaomi MiMo-V2.5 official release/model card · published coding-agent setting
Source: Hugging Face Official Benchmarks data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Source: OpenRouter benchmark exports
22 Apr 2026 version · 90-day results
Across 5 providers lowest 71.2% median 73.8% highest 75%OpenRouter's automatic routing 72.8%
Show results from 5 providers and OpenRouter's automatic routingHide results from 5 providers and OpenRouter's automatic routing
  • GMICloud
  • Venice
  • Xiaomi
  • Novita
  • OpenRouter's automatic routing
  • DeepInfra

Science

GPQA Diamond7 results
Source: OpenRouter benchmark exports
22 Apr 2026 version · 90-day results
Across 6 providers lowest 77% median 82.1% highest 84.9%OpenRouter's automatic routing 78.8%
Show results from 6 providers and OpenRouter's automatic routingHide results from 6 providers and OpenRouter's automatic routing
  • Venice
  • Novita
  • Xiaomi
  • StreamLake
  • OpenRouter's automatic routing
  • GMICloud
  • Parasail

Vision

CharXiv · RQXiaomi MiMo-V2.5 official release/model card · RQ · Code Interpreter setting unspecified · Reported by Xiaomi MiMo · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
MMMU-Pro2 results
Reported by Xiaomi MiMo · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Xiaomi MiMo-V2.5 official release/model card · published multimodal setting
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Video-MME2 results
Reported by Xiaomi MiMo · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Xiaomi MiMo-V2.5 official release/model card · subtitle/audio setting unspecified
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

Reasoning

HR-Bench (4k)2 results
Reported by Xiaomi MiMo · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Xiaomi MiMo-V2.5 official release/model card · 4K
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
VideoHolmes2 results
Reported by Xiaomi MiMo · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Xiaomi MiMo-V2.5 official release/model card · published multimodal setting
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

Math

Instruction following

Speech

General

Knowledge

OCR

Other

Claw-Eval v1.1Reported by Claw-Eval · via BenchBoard docs
ClawEval · General/UnspecifiedXiaomi MiMo-V2.5 official release/model card · text/general subset · Pass³ · exact benchmark version/harness unspecified · Reported by Xiaomi MiMo · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
ClawEval-MM · Pass³Xiaomi MiMo-V2.5 official release/model card · multimodal subset · Pass³ · exact benchmark version/harness unspecified · Reported by Xiaomi MiMo · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
DailyOmni2 results
Reported by Xiaomi MiMo · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Xiaomi MiMo-V2.5 official release/model card · published multimodal setting
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
GraphWalks BFSofficial model-card chart · F1 · Reported by Xiaomi MiMo · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
GraphWalks Parentsofficial model-card chart · accuracy · Reported by Xiaomi MiMo · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OmniCapBench20 related benchmarks · 20 results
Structural · Shot F1
Reported by OmniCapBench authors / Tencent Hunyuan · via BenchBoard docs
OmniCapBench benchmark-owner run · 786 audio-video clips (12.8 hours) · structured MTSS captions · macro average across videos · rule-based structural track with LLM-assisted reference matching · candidate reasoning effort, exact API snapshot and judge model not specified on public leaderboard
Semantic · Non-dialogue event
Reported by OmniCapBench authors / Tencent Hunyuan · via BenchBoard docs
OmniCapBench benchmark-owner run · 786 audio-video clips (12.8 hours) · structured MTSS captions · macro average across videos · bounded localized semantic judging on structurally aligned units · candidate reasoning effort, exact API snapshot and judge model not specified on public leaderboard
Semantic · Scene precision
Reported by OmniCapBench authors / Tencent Hunyuan · via BenchBoard docs
OmniCapBench benchmark-owner run · 786 audio-video clips (12.8 hours) · structured MTSS captions · macro average across videos · bounded localized semantic judging on structurally aligned units · candidate reasoning effort, exact API snapshot and judge model not specified on public leaderboard
Semantic · Scene recall
Reported by OmniCapBench authors / Tencent Hunyuan · via BenchBoard docs
OmniCapBench benchmark-owner run · 786 audio-video clips (12.8 hours) · structured MTSS captions · macro average across videos · bounded localized semantic judging on structurally aligned units · candidate reasoning effort, exact API snapshot and judge model not specified on public leaderboard
Semantic · Shot description
Reported by OmniCapBench authors / Tencent Hunyuan · via BenchBoard docs
OmniCapBench benchmark-owner run · 786 audio-video clips (12.8 hours) · structured MTSS captions · macro average across videos · bounded localized semantic judging on structurally aligned units · candidate reasoning effort, exact API snapshot and judge model not specified on public leaderboard
Semantic · Subject precision
Reported by OmniCapBench authors / Tencent Hunyuan · via BenchBoard docs
OmniCapBench benchmark-owner run · 786 audio-video clips (12.8 hours) · structured MTSS captions · macro average across videos · bounded localized semantic judging on structurally aligned units · candidate reasoning effort, exact API snapshot and judge model not specified on public leaderboard
Show 14 more resultsHide 14 results
Semantic · Subject recall
Reported by OmniCapBench authors / Tencent Hunyuan · via BenchBoard docs
OmniCapBench benchmark-owner run · 786 audio-video clips (12.8 hours) · structured MTSS captions · macro average across videos · bounded localized semantic judging on structurally aligned units · candidate reasoning effort, exact API snapshot and judge model not specified on public leaderboard
Semantic · Subshot precision
Reported by OmniCapBench authors / Tencent Hunyuan · via BenchBoard docs
OmniCapBench benchmark-owner run · 786 audio-video clips (12.8 hours) · structured MTSS captions · macro average across videos · bounded localized semantic judging on structurally aligned units · candidate reasoning effort, exact API snapshot and judge model not specified on public leaderboard
Semantic · Subshot recall
Reported by OmniCapBench authors / Tencent Hunyuan · via BenchBoard docs
OmniCapBench benchmark-owner run · 786 audio-video clips (12.8 hours) · structured MTSS captions · macro average across videos · bounded localized semantic judging on structurally aligned units · candidate reasoning effort, exact API snapshot and judge model not specified on public leaderboard
Semantic table · Dialogue line score
Reported by OmniCapBench authors / Tencent Hunyuan · via BenchBoard docs
OmniCapBench benchmark-owner run · 786 audio-video clips (12.8 hours) · structured MTSS captions · macro average across videos · rule-based dialogue-line measure in the semantic table · candidate reasoning effort, exact API snapshot and judge model not specified on public leaderboard
Structural · Cross-shot coreference
Reported by OmniCapBench authors / Tencent Hunyuan · via BenchBoard docs
OmniCapBench benchmark-owner run · 786 audio-video clips (12.8 hours) · structured MTSS captions · macro average across videos · rule-based structural track with LLM-assisted reference matching · candidate reasoning effort, exact API snapshot and judge model not specified on public leaderboard
Structural · Event-shot association F1
Reported by OmniCapBench authors / Tencent Hunyuan · via BenchBoard docs
OmniCapBench benchmark-owner run · 786 audio-video clips (12.8 hours) · structured MTSS captions · macro average across videos · rule-based structural track with LLM-assisted reference matching · candidate reasoning effort, exact API snapshot and judge model not specified on public leaderboard
Structural · Reference ID usage
Reported by OmniCapBench authors / Tencent Hunyuan · via BenchBoard docs
OmniCapBench benchmark-owner run · 786 audio-video clips (12.8 hours) · structured MTSS captions · macro average across videos · rule-based structural track with LLM-assisted reference matching · candidate reasoning effort, exact API snapshot and judge model not specified on public leaderboard
Structural · Scene reference F1
Reported by OmniCapBench authors / Tencent Hunyuan · via BenchBoard docs
OmniCapBench benchmark-owner run · 786 audio-video clips (12.8 hours) · structured MTSS captions · macro average across videos · rule-based structural track with LLM-assisted reference matching · candidate reasoning effort, exact API snapshot and judge model not specified on public leaderboard
Structural · Schema Gate Compliance
Reported by OmniCapBench authors / Tencent Hunyuan · via BenchBoard docs
OmniCapBench benchmark-owner run · 786 audio-video clips (12.8 hours) · structured MTSS captions · macro average across videos · rule-based structural track with LLM-assisted reference matching · candidate reasoning effort, exact API snapshot and judge model not specified on public leaderboard
Structural · Shot tIoU
Reported by OmniCapBench authors / Tencent Hunyuan · via BenchBoard docs
OmniCapBench benchmark-owner run · 786 audio-video clips (12.8 hours) · structured MTSS captions · macro average across videos · rule-based structural track with LLM-assisted reference matching · candidate reasoning effort, exact API snapshot and judge model not specified on public leaderboard
Structural · Speaker F1
Reported by OmniCapBench authors / Tencent Hunyuan · via BenchBoard docs
OmniCapBench benchmark-owner run · 786 audio-video clips (12.8 hours) · structured MTSS captions · macro average across videos · rule-based structural track with LLM-assisted reference matching · candidate reasoning effort, exact API snapshot and judge model not specified on public leaderboard
Structural · Subject reference F1
Reported by OmniCapBench authors / Tencent Hunyuan · via BenchBoard docs
OmniCapBench benchmark-owner run · 786 audio-video clips (12.8 hours) · structured MTSS captions · macro average across videos · rule-based structural track with LLM-assisted reference matching · candidate reasoning effort, exact API snapshot and judge model not specified on public leaderboard
Structural · Subshot F1
Reported by OmniCapBench authors / Tencent Hunyuan · via BenchBoard docs
OmniCapBench benchmark-owner run · 786 audio-video clips (12.8 hours) · structured MTSS captions · macro average across videos · rule-based structural track with LLM-assisted reference matching · candidate reasoning effort, exact API snapshot and judge model not specified on public leaderboard
Structural · Subshot tIoU
Reported by OmniCapBench authors / Tencent Hunyuan · via BenchBoard docs
OmniCapBench benchmark-owner run · 786 audio-video clips (12.8 hours) · structured MTSS captions · macro average across videos · rule-based structural track with LLM-assisted reference matching · candidate reasoning effort, exact API snapshot and judge model not specified on public leaderboard
OmniDocBench · ScoreXiaomi MiMo-V2.5 official release/model card · higher-is-better score · version unspecified · Reported by Xiaomi MiMo · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Vals9 related benchmarks · 11 results
EMB
Source: Vals AI
CorpFin v2
Source: Vals AI
LegalBench
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
Show 3 more resultsHide 3 results
TaxEval v2
Source: Vals AI

Data credits: 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 · BullshitBench by Peter Gostev, MIT (licence) · BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links. · Data by LLM Stats · OpenRouter public benchmark leaderboard and search-lane exports, CC BY 4.0. Fractional source scores converted to percentages; immutable dated snapshots. (licence) · Hugging Face official benchmark leaderboards; licence varies by benchmark · SnakeBench (Greg Kamradt / ARC Prize Foundation), MIT (licence) · Clinical Benchmarks (clinicalbenchmarks.ai), CC BY 4.0; fractions converted to percentages; source documents retain their own terms (licence)

Also known as: aihubmix/coding-xiaomi-mimo-v2.5, cline-pass/mimo-v2.5, coding-xiaomi-mimo-v2.5, deepinfra/xiaomimimo/mimo-v2.5, gmi/xiaomimimo/mimo-v2.5, mimo-v2.5-free, mimo-v25, mimo/mimo-v2.5, novita/xiaomimimo/mimo-v2.5, opencode_go/mimo-v2.5, xiaomi-mimo-v2-5, xiaomi-mimo-v2.5, xiaomi-mimo-v2.5-free, xiaomi/mimo-v2.5, xiaomi/mimo-v2.5:thinking, xiaomimimo/mimo-v2.5

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