Xiaomi: MiMo-V2-Pro

Xiaomi: MiMo-V2-Pro

xiaomi · Released Mar 18, 2026 Professional
Intelligence #10 / 565
82.0 Our Score
Speed #226 / 266
45.7 tokens / sec
Input #429 / 571
$1.00 per 1M tokens
Output #424 / 571
$3.00 per 1M tokens
Context #17 / 571
1M tokens

Analysis Summary

Xiaomi: MiMo-V2-Pro is developed by Xiaomi. It launched in March 2026, making it a current-generation release. On our leaderboard it earns Professional-tier status, ranking #10 of 565 models in our overall business-suitability ranking. For raw reasoning ability it ranks #23 of 374, putting it in the top quartile for overall intelligence.

For engineering teams, Xiaomi: MiMo-V2-Pro is a standout coder, ranking #36 of 311 on our coding index for code generation, refactoring, and debugging. It also ranks #22 of 286 for agentic, multi-step tasks — the autonomous, tool-driven workflows that underpin business automation. Its 1M-token context window is larger than 97% of the models we list, suiting long documents, large codebases, and retrieval-heavy workloads. It supports tool use and function calling.

At $1.00 input and $3.00 output per 1M tokens, Xiaomi: MiMo-V2-Pro is cost-efficient for everyday workloads so it scales comfortably across routine production traffic. Xiaomi: MiMo-V2-Pro is a dependable pick for businesses that need strong, well-rounded performance without paying frontier prices.

Editorial notes

MiMo-V2-Pro from Xiaomi reaches near-frontier intelligence and agentic scores with a 1M token context, strong instruction following, and tool use at mid-tier pricing.

Assessed May 31, 2026

Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?

Performance Profile

Intelligence7Technical7.3Value7.3Content7.4
Intelligence 7/10
Technical 7.3/10
Content 7.4/10
Value 7.3/10

How Xiaomi: MiMo-V2-Pro compares

Xiaomi: MiMo-V2-Pro ranks #23 of 374 AI models we track for overall intelligence, #36 of 311 for coding, #22 of 286 for agentic tasks. Its 1M-token context window is larger than 97% of the models we list. At $1.00 per million input tokens it is cheaper than 25% of comparable models.

About Xiaomi: MiMo-V2-Pro

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..

Capabilities

Tool Use Function Calling

Performance Indices

Source: Artificial Analysis

49.2 Intelligence Index
41.4 Coding Index
68 Agentic Index

Benchmark Scores

Intelligence

GPQA Diamond 87% Graduate-level scientific reasoning
HLE 28.3% Humanity's Last Exam
SciCode 42.5% Scientific computing

Technical

TerminalBench Hard 40.9% Agentic terminal tasks
τ²-Bench 95% Conversational agent benchmark

Content

IFBench 68.8% Instruction following
LCR 60.7% Long-context reasoning

Benchmark data from Artificial Analysis and Hugging Face

How does Xiaomi: MiMo-V2-Pro stack up?

Compare side-by-side with other professional models.

Compare Models

Model Information

OpenRouter ID xiaomi/mimo-v2-pro
Providerxiaomi
Release Date March 18, 2026
Context Length1,048,576 tokens
Max Completion131,072 tokens
Status Active

Pricing

Token Type Cost per 1M tokens Cost per 1K tokens
Input $1.00 $0.001000
Output $3.00 $0.003000

Leaderboard Categories

Frequently asked questions about Xiaomi: MiMo-V2-Pro

How much does Xiaomi: MiMo-V2-Pro cost?

Xiaomi: MiMo-V2-Pro costs $1.00 per million input tokens and $3.00 per million output tokens.

What is the context window of Xiaomi: MiMo-V2-Pro?

Xiaomi: MiMo-V2-Pro has a context window of 1,048,576 tokens (1M).

Is Xiaomi: MiMo-V2-Pro good for coding?

On our coding benchmark index, Xiaomi: MiMo-V2-Pro ranks #36 of 311 models, placing it in the top quartile of the field for code generation and debugging.

What can Xiaomi: MiMo-V2-Pro do?

Xiaomi: MiMo-V2-Pro supports tool use and function calling.

Who created Xiaomi: MiMo-V2-Pro?

Xiaomi: MiMo-V2-Pro is developed by Xiaomi and was released on March 18, 2026.