Private AI
Xiaomi MiMo V2 Flash with explicit thinking mode enabled. Shows the model's reasoning process before responses. Same 309B MoE architecture (15B active) as the base model, but outputs thinking/reasoning tokens for transparency. Best for complex reasoning tasks where you want to see the model's thought process. Routed directly to Xiaomi, so no logging guarantees may be limited.
Context Window
256.0K
Max Output
32.8K
Input Price (Auto)
$0.10/1M
Output Price (Auto)
$0.31/1M
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
39.2
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Coding Index
31.8
GPQA Diamond
Graduate-level scientific reasoning
84.6%
Better than 85% of models compared
HLE
Humanity's Last Exam
21.1%
Better than 84% of models compared
IFBench
Instruction-following benchmark
64.2%
Better than 75% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
95.0%
Better than 93% of models compared
AA-LCR
Long context reasoning evaluation
63.0%
Better than 78% of models compared
SciCode
Python programming for scientific computing
39.4%
Better than 72% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
28.0%
AIME 2025
American Invitational Mathematics Examination 2025
96.3%
Better than 98% of models compared
MMLU-Pro
Professional and academic subject knowledge
84.3%
Better than 89% of models compared
Last updated Jun 4, 2026
Artificial AnalysisBetter than 69% of models compared
LiveCodeBench
Contamination-free coding benchmark
86.8%
Better than 97% of models compared
