TAU2
Measured May 29, 2026Source
Score
0.93
Models13 1 
MiMo-V2-Flash (Feb 2026)
XiaomiXiaomiChina
MiMo-V2-Flash is a fast and efficient multimodal AI model from Xiaomi, optimized for on-device and edge deployment. It is the second generation in the MiMo series, focusing on rapid inference and low-latency responses for mobile and IoT applications.
FastMultimodalReasoning
Input / 1M tokens
$0.10Output / 1M tokens
$0.30Output tokens/s
134.22First-token seconds
1.66sSupported plans
4Benchmark history
Evaluations
Terminalbench Hard
Measured May 29, 2026Source
Score
0.31
Lcr
Measured May 29, 2026Source
Score
0.64
Ifbench
Measured May 29, 2026Source
Score
0.72
Scicode
Measured May 29, 2026Source
Score
0.38
Hle
Measured May 29, 2026Source
Score
0.2
Gpqa
Measured May 29, 2026Source
Score
0.84
Artificial Analysis Coding Index
Measured May 29, 2026Source
Score
33.5
Artificial Analysis Intelligence Index
Measured May 29, 2026Source
Score
41.5
Aime 25
Measured May 29, 2026Source
Score
0.96
Livecodebench
Measured May 29, 2026Source
Score
0.87
Mmlu Pro
Measured May 29, 2026Source
Score
0.84
Artificial Analysis Math Index
Measured May 29, 2026Source
Score
96.3
Plan availability
Products and plans that support this model
Xiaomi MiMo Token Plan
Xiaomi MiMo Token Plan
Xiaomi MiMo Token Plan is a subscription service offering credits-based access to Xiaomi's MiMo AI models, including V2.5 and V2 series, via OpenAI-compatible and Anthropic APIs. Designed for developers and coding enthusiasts, it integrates with popular coding tools and provides transparent pricing with tiered packages.
User ratings
Loading ratings...
Discussion
Thinking... Make sure you are connected to GitHub server