MiMo-V2.5
by Xiaomitext+image+audio+video->text7 endpoints
Neura Intelligence Index
50.1/ 100
Rank
#149—
Confidence
lowBenchmarks
3(8% coverage)
Overview
MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...
Capabilities
Text generation
Image understanding
Audio processing
Video understanding
Tool use / Function calling
Structured output
Modalities
Input
TextAudioImageVideo
Output
Text
Technical Specifications
Context Window
1.0M tokens
Max Output
131.1K tokens
Tokenizer
Other
Uptime (24h)
9919.1%
Parameters
310775040000B
License
mitOpen Weights
Supported Parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Benchmark Performance
coding
| Benchmark | Score | Source |
|---|---|---|
| SWE-Bench Pro | 56.1 | verified |
multimodal
| Benchmark | Score | Source |
|---|---|---|
| CharXiv Reasoning | 81 | verified |
| MMMU-Pro | 77.9 | verified |
Performance Over Time
Pricing
Per 1M tokens
Input$0.14
Output$0.28
Cache read$0.0028