Home/Models/MiMo-V2-Pro
xiaomi logo

MiMo-V2-Pro

by xiaomi · Released Mar 2026

1M Context
62.9
avg score
Rank #56
Compare
Better than 76% of all models
Context
1.0M tokens (~524 books)
Input $/1M
$1.00
Output $/1M
$3.00
Type
text
License
Proprietary
Benchmarks
13 tested
Data updated today
About

MiMo-V2-Pro is Xiaomi's flagship foundation model, featuring over 1T total parameters and a 1M context length, deeply optimized for agentic scenarios. It is highly adaptable to general agent frameworks like...

Tested on 13 benchmarks with 58.1% average. Top scores: Chatbot Arena Elo — Overall (1445.0%), Chatbot Arena Elo — Coding (1433.4%), LiveBench — Mathematics (77.0%).

Looking for similar performance at lower cost?
Qwen3 30B A3B Thinking 2507 scores 63.5 (101% as good) at $0.08/1M input · 92% cheaper
Capabilities
coding
49.4
#68 globally
reasoning
59.5
#32 globally
math
77.0
#22 globally
knowledge
58.1
#57 globally
speed
85.2
#11 globally
language
56.1
#97 globally
Benchmark Scores
Compare All
Tested on 13 benchmarks · Ranked across 7 categories
Score Distribution (all 233 models)
0255075100
▲ You are here
LiveBench — Coding

Regularly refreshed coding problems that avoid data contamination. New problems added monthly to prevent memorization.

68.8
LiveBench — Agentic Coding

LiveBench coding tasks that require multi-step reasoning and tool use. Tests planning and execution of complex coding workflows.

30.0
LiveBench — Reasoning

Regularly refreshed reasoning problems testing logical deduction, spatial reasoning, and analytical thinking.

69.7
LiveBench — Data Analysis

Fresh data analysis tasks testing ability to interpret tables, charts, and statistical data.

49.2
LiveBench — Mathematics

Regularly updated math problems that test numerical reasoning, algebra, calculus, and combinatorics.

77.0
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Links
Documentation
Community
BenchGecko API
mimo-v2-pro
Specifications
  • Typetext
  • Context1.0M tokens (~524 books)
  • ReleasedMar 2026
  • LicenseProprietary
  • StatusActive
  • Cost / Message~$0.005
Available On
xiaomi logoxiaomi$1.00
Share & Export
Tweet
MiMo-V2-Pro is a proprietary text AI model by xiaomi, released in March 2026. It has an average benchmark score of 62.9. Context window: 1M tokens.