Xiaomi
Xiaomi

MiMo-V2-Pro

Model ID:xiaomi/mimo-v2-pro
2026-03-18Proprietary Model
API
OverallNo.7
PopularityNo.34

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 OpenClaw. It ranks among the global top tier in the standard PinchBench and ClawBench benchmarks, with perceived performance approaching that of Opus 4.6. MiMo-V2-Pro is designed to serve as the brain of agent systems, orchestrating complex workflows, driving production engineering tasks, and delivering results reliably.

Knowledge Cutoff
Unknown

The date this AI finished learning. It may not know about things that happened after this date.

Input → Output Format

The types of content this AI can receive, and what it can produce in return.

Context Memory
1.0MIN131KOUT

The maximum amount of text the AI can read and process in a single request. A larger number means it can handle longer documents or conversations.

Cost/1M Words
$1IN$3OUT

The cost of using this AI directly in your own application. Shown in USD per 1 million units of text (tokens).

AI Performance Evaluation

Arena Overall Score
1447
±7
As of 2026-04-02
Overall Rank
No.34
6,804 Votes
Arena by Ability
Hard Prompts
1478±9No.24
Expert Knowledge
1514±27No.5
Instruction Following
1448±13No.23
Conversation Memory
1460±17No.29
Creative
1432±19No.24
Coding
1504±14No.26
Math
1444±25No.31
Arena by Occupation
Creative Writing
1435±15No.25
Social Sciences
1489±18No.7
Media
1434±18No.20
Business
1455±16No.23
Healthcare
1484±27No.20
Legal
1465±27No.24
Software
1482±12No.34
Mathematics
1453±29No.27
Reasoning Ability
AA Intelligence Index
49%↑10%
GPQA Diamond
87%↑5%
HLE
28%↑12%
Coding Ability
AA Coding Index
41%↑5%
SciCode
43%↑0%
TerminalBench
41%↑7%
Instruction Following
IFBench
69%↑12%
Long Context
AA-LCR
61%↓3%
Agentic AI Ability
TAU2
95%↑24%
Speed
Standard Mode
32tok/sec↓46
First Output 2.85s
OpenRouter