Home/Models/MiMo-V2.5
xiaomi logo

MiMo-V2.5

by xiaomi · Released Apr 2026

Open SourceMultimodal1M Context
Compare
Context
1.1M tokens (~525 books)
Input $/1M
$0.14
Output $/1M
$0.28
Type
multimodal
License
Open Source
Benchmarks
3 tested
Data updated today
About

MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...

Tested on 3 benchmarks with 0.0% average. Top scores: Chatbot Arena Elo — Overall (1433.0%), Chatbot Arena Elo — Coding (1432.1%), Artificial Analysis — Quality Index (40.1%).

Capabilities
speed
66.9
#35 globally
Benchmark Scores
Compare All
Tested on 3 benchmarks · Ranked across 2 categories
Score Distribution (all 274 models)
0255075100
Chatbot Arena Elo — Overall

Chatbot Arena overall Elo rating. Crowdsourced human preference ranking from blind head-to-head comparisons across all topics.

1433
Chatbot Arena Elo — Coding

Chatbot Arena coding Elo. Human preference ranking specifically for coding tasks and technical questions.

1432
Artificial Analysis — Quality Index

Artificial Analysis Quality Index. Composite quality score combining multiple benchmark results into a single metric.

40.1
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Links
Documentation
Community
BenchGecko API
mimo-v2-5
Specifications
  • Typemultimodal
  • Context1.1M tokens (~525 books)
  • ReleasedApr 2026
  • LicenseOpen Source
  • StatusActive
  • Cost / Message~$0.001
Available On
xiaomi logoxiaomi$0.14
Categories
Share & Export
Tweet
MiMo-V2.5 is an open-source multimodal AI model by xiaomi, released in April 2026. Context window: 1M tokens.