llmboard.ai
Benchmarks
CompareRankings
llmboard.ai
Benchmarks
CompareRankings
HomeModelsMiMo

Xiaomi model product

MiMo

MiMo-V2.5 is Xiaomi's native omnimodal sparse Mixture-of-Experts model with 310B total parameters, 15B activated parameters, and a 1M-token context window. Built on the MiMo-V2-Flash backbone, it adds dedicated vision and audio encoders for text, image, video, and audio understanding, and is post-trained with SFT, agentic reinforcement learning, and Multi-Teacher On-Policy Distillation for multimodal perception, long-context reasoning, and agentic workflows.

Updated Aug 10, 2026. Default version: MiMo-V2.5

Compare
LLMBoard scoreN/ANot scored
CoverageN/ANo published score
Context window1MTokens
Official input price$0.14Xiaomi API

On this page

  • Specification
  • Capability
  • Benchmarks
  • Arena
  • Pricing
  • Versions
  • About
  • Similar models
  • FAQ

Model specification

Structured fields from the published default version.

Version
MiMo-V2.5
Released
Apr 22, 2026
Knowledge cutoff
Dec 1, 2024
Parameters
310.8B
Context window
1M
Max output
131.1K
Inputs
audio, image, text, video
Outputs
text
Open weights
Yes
License
MIT

Capability profile

This profile uses the latest version under this unique model that has a calculated LLMBoard score. Arena and price are excluded.

No capability profile

No published version under this unique model currently has enough benchmark coverage to calculate a score.

Benchmark results

Published benchmark records for the scored version currently unavailable.

No benchmark rows

No published benchmark result is linked to the scored version.

Arena results

Preference and agent-evaluation signals from published Arena datasets.

100 rows
Columns

Show columns

vision style controlchinese251315.5981N/AAug 6, 2026
visionchinese281326.2981N/AAug 6, 2026
text factualitykorean301376.8422N/AAug 6, 2026
text factualityindustry mathematical331451.71,925N/AAug 6, 2026
text factualityfrench351473.51,360N/AAug 6, 2026
text factualitymath351447.71,891N/AAug 6, 2026
visionentity recognition361195.9143N/AAug 6, 2026
visionenglish381263.48,578N/AAug 6, 2026
vision style controlentity recognition381171.5143N/AAug 6, 2026
text factualityjapanese391335.5364N/AAug 6, 2026
visiondiagram401274.15,611N/AAug 6, 2026
texthard prompts english421461.614,080N/AAug 6, 2026
text factualityspanish431431.21,030N/AAug 6, 2026
visionocr431261.915,030N/AAug 6, 2026
vision style controldiagram431270.55,611N/AAug 6, 2026
text factualitycoding441504.112,146N/AAug 6, 2026
visionhumor451232.8752N/AAug 6, 2026
visionoverall461251.420,781N/AAug 6, 2026
vision style controlenglish461244.38,578N/AAug 6, 2026
text factualitychinese471486.21,724N/AAug 6, 2026
text factualityhard prompts english471482.013,528N/AAug 6, 2026
vision style controlhumor471220.2752N/AAug 6, 2026
vision style controlocr471252.915,030N/AAug 6, 2026
webdevwebdev-react471426.38,771N/AAug 6, 2026
text factualityindustry software and it services481487.117,742N/AAug 6, 2026
visionhomework481267.23,082N/AAug 6, 2026
vision style controlhomework481260.33,082N/AAug 6, 2026
webdevoverall481436.910,952N/AAug 6, 2026
webdevwebdev481436.910,952N/AAug 6, 2026
text factualityexpert491478.73,533N/AAug 6, 2026
vision style controloverall501237.720,781N/AAug 6, 2026
textcoding511469.312,790N/AAug 6, 2026
textindustry business and management and financial operations511433.29,008N/AAug 6, 2026
textinstruction following511434.114,726N/AAug 6, 2026
textlonger query521445.519,336N/AAug 6, 2026
text factualitylonger query521462.318,822N/AAug 6, 2026
textexpert531462.74,248N/AAug 6, 2026
textindustry mathematical531450.52,398N/AAug 6, 2026
text factualityinstruction following531443.314,157N/AAug 6, 2026
texthard prompts541449.929,501N/AAug 6, 2026
visioncreative writing vision541226.51,122N/AAug 6, 2026
textindustry software and it services551462.618,028N/AAug 6, 2026
text factualityindustry business and management and financial operations551452.28,000N/AAug 6, 2026
webdevwebdev-html551426.01,279N/AAug 6, 2026
vision style controlcreative writing vision561209.51,122N/AAug 6, 2026
text factualityenglish581456.420,036N/AAug 6, 2026
text factualityhard prompts581469.729,460N/AAug 6, 2026
text style controlindustry mathematical581455.42,398N/AAug 6, 2026
text factualitymulti turn591457.86,781N/AAug 6, 2026
textenglish611447.520,068N/AAug 6, 2026
textmulti turn621444.37,841N/AAug 6, 2026
text style controlexpert651474.34,248N/AAug 6, 2026
textmath661438.82,318N/AAug 6, 2026
text style controllonger query661452.819,336N/AAug 6, 2026
text factualityindustry entertainment and sports and media671411.48,958N/AAug 6, 2026
text style controlchinese671484.62,113N/AAug 6, 2026
text style controlhard prompts english671472.214,080N/AAug 6, 2026
text style controlmath671441.42,318N/AAug 6, 2026
text style controlenglish691453.020,068N/AAug 6, 2026
text factualityindustry life and physical and social science701462.36,206N/AAug 6, 2026
text style controlcoding711491.012,790N/AAug 6, 2026
text style controlmulti turn711450.67,841N/AAug 6, 2026
textchinese731471.52,113N/AAug 6, 2026
text style controlhard prompts731462.029,501N/AAug 6, 2026
text style controlindustry business and management and financial operations731442.79,008N/AAug 6, 2026
text style controlindustry software and it services731479.318,028N/AAug 6, 2026
text style controlinstruction following731431.714,726N/AAug 6, 2026
text factualityindustry writing and literature and language751419.110,014N/AAug 6, 2026
textfrench761445.01,734N/AAug 6, 2026
text factualityoverall771439.144,129N/AAug 6, 2026
text factualityindustry legal and government771442.92,887N/AAug 6, 2026
textoverall801427.644,200N/AAug 6, 2026
text factualityexclude ties811434.533,819N/AAug 6, 2026
text factualityindustry medicine and healthcare811455.62,494N/AAug 6, 2026
textexclude ties821417.133,875N/AAug 6, 2026
textindustry entertainment and sports and media821398.19,591N/AAug 6, 2026
text factualitycreative writing821405.36,275N/AAug 6, 2026
text style controlindustry life and physical and social science821453.47,119N/AAug 6, 2026
textindustry writing and literature and language831407.910,640N/AAug 6, 2026
text factualityrussian831420.33,914N/AAug 6, 2026
text style controlfrench831452.91,734N/AAug 6, 2026
text style controlindustry entertainment and sports and media841402.39,591N/AAug 6, 2026
text style controlindustry writing and literature and language841411.410,640N/AAug 6, 2026
textindustry life and physical and social science851439.87,119N/AAug 6, 2026
text style controloverall851434.044,200N/AAug 6, 2026
text style controlexclude ties851427.733,875N/AAug 6, 2026
text style controlpolish851419.5929N/AAug 6, 2026
text style controlgerman871421.8749N/AAug 6, 2026
textpolish881413.0929N/AAug 6, 2026
text factualitynon english901418.224,086N/AAug 6, 2026
text style controlindustry medicine and healthcare911447.93,106N/AAug 6, 2026
textgerman941409.0749N/AAug 6, 2026
textkorean941363.2786N/AAug 6, 2026
text style controlkorean941371.0786N/AAug 6, 2026
text style controlnon english941411.224,131N/AAug 6, 2026
textcreative writing961391.87,236N/AAug 6, 2026
textspanish961413.61,362N/AAug 6, 2026
textindustry medicine and healthcare981429.03,106N/AAug 6, 2026
text style controlspanish991412.21,362N/AAug 6, 2026
text style controlcreative writing1001394.07,236N/AAug 6, 2026

Pricing

Official vendor API PAYG pricing is summarized first. The table then lists individual provider offerings without treating their minimum as the official price.

Official API
$0.14 input, $0.28 output per 1M
Official provider
Xiaomi
Lowest third-party
From $0.14 input, $0.28 output per 1M via OpenCode Go
Tracked offerings
6
6 rows
Columns

Show columns

Xiaomi Token Plan (China)mimo-v2.5globalN/AN/A1MAug 7, 2026
Xiaomi Token Plan (Europe)mimo-v2.5globalN/AN/A1MAug 7, 2026
Xiaomi Token Plan (Singapore)mimo-v2.5globalN/AN/A1MAug 7, 2026
OpenCode Gomimo-v2.5global$0.14$0.281MAug 7, 2026
LLM Gatewaymimo-v2.5global$0.14$0.281MAug 7, 2026
Xiaomimimo-v2.5global$0.14$0.281MAug 7, 2026

Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.

MiMo versions

All published versions linked to this unique model. The score columns identify the version used by the current overall ranking.

1 rows
Columns

Show columns

MiMo-V2.5Apr 22, 2026N/A310.8B1M131.1KYesMIT

What is MiMo?

A concise description based on the published model registry.

MiMo-V2.5 is Xiaomi's native omnimodal sparse Mixture-of-Experts model with 310B total parameters, 15B activated parameters, and a 1M-token context window. Built on the MiMo-V2-Flash backbone, it adds dedicated vision and audio encoders for text, image, video, and audio understanding, and is post-trained with SFT, agentic reinforcement learning, and Multi-Teacher On-Policy Distillation for multimodal perception, long-context reasoning, and agentic workflows.

Use the benchmark, Arena and pricing sections above as separate evidence. A missing field means the current data snapshot does not support that claim.

Data snapshot: 2026-08-07. Editorial model content is not available in the backend.

Models similar to MiMo

Recommendations prioritize the same model type and family, then the closest published LLMBoard score.

#63
XI

MiMo V2 Flash

Xiaomi

55.9 LLMBoard

DetailsCompare
#35
XI

MiMo V2.5 Pro

Xiaomi

68.9 LLMBoard

DetailsCompare
#170
AC

Qwen3.5 0.8B

Alibaba Cloud / Qwen Team

0.3 LLMBoard

DetailsCompare
#169
GO

Gemma 3 1B

Google

2.7 LLMBoard

DetailsCompare
#168
GO

Gemma 3n E2B

Google

6.9 LLMBoard

DetailsCompare
#167
AC

Qwen3 VL 4B

Alibaba Cloud / Qwen Team

7.7 LLMBoard

DetailsCompare

FAQ

Common questions about MiMo.

When was MiMo released?

MiMo's default version was released on Apr 22, 2026.

How much does MiMo cost?

MiMo's official API price is $0.14 per million input tokens and $0.28 per million output tokens via Xiaomi. The lowest tracked third-party offer starts at $0.14 input and $0.28 output via OpenCode Go.

Who created MiMo?

MiMo is published under Xiaomi in the model registry.

What is the context window for MiMo?

The default version has a 1M token context window.

Is MiMo open weight?

Yes. The default version is marked as open weight under MIT.

How many API providers offer MiMo?

6 published provider offerings are linked to the default version.

What models should I compare MiMo with?

No nearby ranked alternatives are currently available.

Rankings

OverallCodingText ArenaPricing

Modalities

Image GenerationVideo GenerationSpeech-to-TextEmbeddings

Benchmarks

All BenchmarksReasoningMathCoding

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai