MiMo V2 Omni is Xiaomi's language model. A dated release of Xiaomi's MiMo V2 Omni multimodal model, supporting image, video, and audio inputs in a unified agentic architecture.
Specifications
Canonical IDxiaomi-mimo-2-omni-0327
TypeLanguage
StatusActive
CreatorXiaomiXiaomi
Input ModalitiesText
Output ModalitiesText
Benchmarks
Intelligence Index
#79
GPQA
#86
HLE
#102
IFBench
#83
Time to First Token
#310
SciCode
#152
LCR
#97
TerminalBench Hard
#66
TAU2
#77
Output TPS
#532

Capabilities

Input1/5
Text
Image·
Audio·
Video·
PDF·
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
MiMo V2.5 Pro1.1M$0.435$0.870Available
MiMo V2.51.1M$0.140$0.280Available
MiMo V2 Pro1.0MDeprecated
MiMo V2 Omni262KDeprecated
MiMo V2 Flash262K$0.100$0.300Deprecated
MiMo V2 OmniCurrent
MiMo V2.5 424BAvailable
MiMo V2Available
MiMo V2 Flash ReasoningAvailable
MiMo V2 TTSAvailable
MiMo V2.5 TTSAvailable

Model IDs

mimo-v2-omni-0327
xiaomi-mimo-2-omni-0327