Skip to content

Xiaomi · Chat

MiMo V2.5 Pro

Xiaomi 🇨🇳ChatMiMo familyOpen weights. One of its sources says the weights are publicly available.

Newer version: MiMo V2.6 Pro. We compared release dates and version names in our catalogue.

From Neosantara's listing:
MiMo-V2.5-Pro is the flagship reasoning model from Xiaomi, built for general agentic capability, complex software engineering, and long-horizon tasks. Its 1M token context window lets it carry out professional work that would otherwise take human experts days or weeks, spanning more than a thousand tool calls.
llminfo IQ
128.0
Max context
1.1M
Listings
36

Evidence and sources

🤗 XiaomiMiMo/MiMo-V2.5-Prollminfo IQ 128.0, ranked among chat models. From 172 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 106.5, 95% interval 101–112. From 16 benchmark families across 7 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 (59.5). 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 34,021 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: #173 on OpenRouter today #187 on NanoGPT recently #194 on OpenRouter this week #196 on OpenRouter this monthSources: LMArena data, Models.dev data, AI/ML API data, Neosantara Inference data, Hugging FacePrimary data from LMArena from Models.dev: weights availability from AI/ML API: primary mode from Neosantara Inference: description from Hugging Face: release date

Advantages and trade-offs

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

Advantages

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 04:34 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 10 maker's prices.

Input & output

as stated by the model's providers
Text
Images
Text

Capabilities

Supported operations and provider-stated features

VisionReasoningFunction callingStructured outputPrompt caching

Listings

 Xiaomimimo-v2.5-pro · fp8Source: Models.dev data1M$0.435cache read $0.0036$0.87
 Aihubmixaihubmix/coding-xiaomi-mimo-v2.5-pro · codingSource: LiteLLM data1M$0.20cache read $0.0016$0.40
 Gmicloudgmi/XiaomiMiMo/MiMo-V2.5-ProSource: LiteLLM data1.1M$0.3045cache read $0.0025$0.609
 Avianxiaomi/mimo-v2.5-proSource: Avian.io Models data1M$0.3698cache read $0.0031$0.7395
 Atlascloudxiaomi/mimo-v2.5-pro · fp8Source: AtlasCloud data1M$0.435cache read $0.0036$0.87
 Cometapimimo-v2.5-proSources: CometAPI data, CometAPI Pricing dataNot published by the provider$0.435$0.87
 MeganovaXiaomiMiMo/MiMo-V2.5-ProSource: MegaNova data1M$0.435$0.87
 Llmtrmimo/mimo-v2.5-proSource: Models.dev data1M$0.435$0.87
 Neosantaramimo-v2.5-proSource: Neosantara Inference data1M$0.435cache read $0.0036$0.87
 Opencode Goopencode_go/mimo-v2.5-proSources: LiteLLM data, Models.dev data1M$0.435cache read $0.0036$0.87
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, Cline Pass, DeepInfra, Digitalocean, Hugging Face, Kilo, NanoGPT, Nous Portal, Novita AI, Openroute Cn, OpenRouter, Requesty, Standardcompute, Zenmux.

2 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 ELO53 related benchmarks · 53 results
Source: LMArena data · Nov 2026
BenchmarkScore
Arena ELO
Chinese
Creative Writing
English
Show 49 more benchmarksHide 49 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 - German
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 - Polish
Text Factuality - Russian
Text Factuality - Spanish
Design Arena EloSource: Design Arena Leaderboards data · Nov 2026

Coding

Arena ELOSource: LMArena data · Nov 2026
MBPP+Source: 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-Pro official launch table · Xiaomi internal coding-agent evaluation · frameworks such as Claude Code
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
SWE-bench Verified5 related benchmarks · 6 results
SWE-bench Verified
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-Pro official launch table · 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
ValsSource: Vals AI

Agentic

GDPval-AAXiaomi MiMo-V2.5-Pro official launch table · provider-reported comparison table · Reported by Xiaomi MiMo · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
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-Pro official launch table · 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 6 providers lowest 45.9% median 72% highest 74%OpenRouter's automatic routing 72.9%
Show results from 6 providers and OpenRouter's automatic routingHide results from 6 providers and OpenRouter's automatic routing
  • StreamLake
  • Novita
  • OpenRouter's automatic routing
  • Xiaomi
  • DeepInfra
  • DigitalOcean
  • AtlasCloud
TAU3-Bench2 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-Pro official launch table · aggregate/domain and harness unspecified
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

Long context

Reasoning

ARC-CSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
BBHSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
C-EvalSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
DROPSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
HellaSwagSource: 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-Pro official launch table · without tools
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

Science

GPQASource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
GPQA Diamond8 results
Source: OpenRouter benchmark exports
22 Apr 2026 version · 90-day results
Across 7 providers lowest 62.5% median 85.5% highest 87.4%OpenRouter's automatic routing 82.1%
Show results from 7 providers and OpenRouter's automatic routingHide results from 7 providers and OpenRouter's automatic routing
  • StreamLake
  • DeepInfra
  • Xiaomi
  • Novita
  • DigitalOcean
  • OpenRouter's automatic routing
  • GMICloud
  • AtlasCloud

Math

AIMESource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
MATHSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

General

Knowledge

TriviaQASource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Instruction following

Multilingual

Vision

Other

Claw-Eval v1.1Reported by Claw-Eval · via BenchBoard docs
ClawEval · General/UnspecifiedXiaomi MiMo-V2.5-Pro official launch table · Pass³ · exact benchmark version/subset/harness unspecified · Reported by Xiaomi MiMo · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
CMMLUSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
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.
WildClawBench6 related benchmarks · 6 results
WildClawBench
Source: Hugging Face Official Benchmarks data · Reported by the model's developer. The source relaying it did not verify it. claim
Multimodal (26 tasks)
Reported by WildClawBench / InternLM · via BenchBoard docs
OpenClaw · multimodal-input split · 26 tasks
Overall
Reported by WildClawBench / InternLM · via BenchBoard docs
OpenClaw · full 60-task suite
Pure-text (34 tasks)
Reported by WildClawBench / InternLM · via BenchBoard docs
OpenClaw · pure-text split · 34 tasks
Total Cost
Reported by WildClawBench / InternLM · via BenchBoard docs
OpenClaw · full 60-task suite
Total Elapsed
Reported by WildClawBench / InternLM · via BenchBoard docs
OpenClaw · full 60-task suite

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 · BullshitBench by Peter Gostev, MIT (licence) · Hugging Face official benchmark leaderboards; licence varies by benchmark · 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. · EQ-Bench (Samuel J. Paech) — cite paech2023eqbench · 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) · SnakeBench (Greg Kamradt / ARC Prize Foundation), MIT (licence)

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