MiMo-V2.5on Krater.ai
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
Released April 22, 2026
Specifications
MiMo-V2.5 at a glance
Context
1.1M tokens
Max output
131.1K tokens
Input
Text, Audio, Image, Video
Output
Text
Input price
$0.14 / 1M
Output price
$0.28 / 1M
Capabilities
What it is good at
Catalog capabilities
- Accepts image input
- Generates text responses
- Supports tool calling
- Supports structured outputs
Good for
Benchmarks
Catalog data, not Krater benchmarks.
Coding index score
56.8
Agentic index score
15.8
Intelligence index score
25.2
Design Arena dataviz rank
#30
Design Arena website rank
#31
Compare
Compare MiMo-V2.5
MiMo-V2.5 vs MiMo-V2.6-Flash
MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi.
Open comparisonMiMo-V2.5 vs MiMo-V2.6-Pro
MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi. Built at a scale of over 1T parameters, it is designed to push the ceiling of capability for the most demanding
Open comparisonMiMo-V2.5 vs MiMo-V2.6-Pro-UltraSpeed
MiMo-V2.6-Pro-UltraSpeed is the fast speed edition of Xiaomi's flagship foundation model, MiMo-V2.6-Pro.
Open comparisonFAQ
Questions about MiMo-V2.5
Clear answers based on the model catalog and Krater access.