MiMo-V2-Omni
XiaomiProprietary
Description
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.
Release Date
2026-03-19
Parameters
—
Context Length
262K
Modalities
audio, image, text, video
Capability Radar
38
general
36
coding
83
reasoning
54
scienceest.
100
agents
85
multimodal
Science uses a reasoning proxy when dedicated science benchmarks are unavailable.
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Agents & Tools | 61 | 54.0 | LS |
| Code Ranking | 75 | 66.0 | AA |
| General Ranking | 74 | 73.0 | AA |
| Science | 82 | 64.0 | AA |
Benchmark Scores (LLM Stats)
Agents
GDPval-AA
1410.00 / 3000SR
PinchBench
81.2%SR
Claw-Eval
54.8%SR
MM-BrowserComp
52.0%SR
OmniGAIA
49.8%SR
Code
SWE-Bench Verified
74.8%SR
AA Evaluation Indices
Intelligence Index43.4
Coding Index35.5
Tau20.9
Gpqa0.8
Lcr0.7
Ifbench0.5
Scicode0.4
Terminalbench Hard0.3
Hle0.2
LLM Stats Category Scores
Finance100
General100
Legal100
Reasoning100
Agents100
Code70
Coding70
Frontend Development70
Pricing
Input PriceFree
Output PriceFree
Blended Price (3:1)Free
Speed
Tokens/sec120.9 tokens/s
Time to First Token1.35s
Time to Answer17.89s
Available Providers
(LS internal units)| Provider | Input Price | Output Price |
|---|---|---|
| Xiaomi | 400K | 2.0M |