MiMo-V2-Flash

Non-reasoning

Creator

Xiaomi

Released

2025-12-16

Intelligence

24.7

Artificial Analysis Index

Coding

49.8

Artificial Analysis Index

In $/1M

$0.00

input tokens

Out $/1M

$0.00

output tokens

Blended $/1M

$0.00

3:1 blended

Speed

0

tokens / sec

Profile

License, openness, and modality — the governance layer.

License

MIT

commercial OK

Weights

Open

downloadable

Modalities

Text

Parameters

309B

total

MiMo-V2-Flash is a powerful, efficient, and ultra-fast foundation language model that excels in reasoning, coding, and agentic scenarios. It is a Mixture-of-Experts model with 309B total parameters and 15B active parameters, featuring a hybrid attention architecture with sliding-window and full attention (5:1 ratio, 128-token window). Delivers 150 tokens/sec inference with 256k context window.

Capability profile

Category strength across 20 domains, via LLM Stats.

writing
90creativity
90legal
80biology
80finance
80physics
80language
80chemistry
80healthcare
80math
70
general
70reasoning
70frontend development
70search
60tool calling
60structured output
60code
50agents
50long context
50vision
20
Via LLM Stats

Benchmark breakdown

Independent evaluation scores, normalized to 0–100.

GPQA Diamond
66
Humanity’s Last Exam
8
MMLU-Pro
74
SciCode
26
LiveCodeBench
40
MATH-500
AIME 2025
68
τ²-Bench (agentic)
84
Terminal-Bench Hard
26
IFBench
40
Via Artificial Analysis
© 2026 NYSGPT2525 LLC