MiMo-V2-Omni

Creator

Xiaomi

Released

2026-03-19

Intelligence

35.0

Artificial Analysis Index

Coding

Artificial Analysis Index

In $/1M

$0.00

input tokens

Out $/1M

$0.00

output tokens

Blended $/1M

$0.00

3:1 blended

Speed

0

tokens / sec

Profile

License, openness, and modality — the governance layer.

License

Proprietary

non-commercial

Weights

Closed

API only

Modalities

Audio · Image · Text · Video

Parameters

MiMo-V2-Omni is Xiaomi's omni foundation model uniting frontier multimodal understanding with strong agentic capability. It fuses dedicated image, video, and audio encoders into a single shared backbone, processing all modalities simultaneously. Natively supports structured tool calling, function execution, and UI grounding. Supports over 10 hours of continuous audio understanding and 256K token context window.

Capability profile

Category strength across 20 domains, via LLM Stats.

legal
100finance
100reasoning
100agents
100
general
100code
70frontend development
70
Via LLM Stats

Benchmark breakdown

Independent evaluation scores, normalized to 0–100.

GPQA Diamond
83
Humanity’s Last Exam
20
MMLU-Pro
SciCode
37
LiveCodeBench
MATH-500
AIME 2025
τ²-Bench (agentic)
91
Terminal-Bench Hard
35
IFBench
54
Via Artificial Analysis
© 2026 NYSGPT2525 LLC