MiMo-V2-Flash (Non-reasoning)
XiaomiOpen WeightMIT · Commercial OK
Description
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.
Release Date
2025-12-16
Parameters
309.0B
Context Length
—
Modalities
text
Capability Radar
70
general
50
coding
70
reasoning
68
scienceest.
60
agents
0
multimodal
Science is estimated from LLM Stats science scores or reasoning when no dedicated science benchmarks are available.
Rankings
No ranking data available
Benchmark Scores (LLM Stats)
(LLM Stats (zeroeval))General
Arena-Hard v2
86.2%SR
Tau-bench
80.3%SR
Language
MMLU-Pro
84.9%SR
Long Context
LongBench v2
60.6%SR
MRCR
45.7%SR
Math
AIME 2025
94.1%SR
HMMT 2025
84.4%SR
Reasoning
GPQANYU + Cohere + Anthropic (2023)
83.7%SR
LiveCodeBench v6
80.6%SR
SWE-Bench Verified
73.4%SR
SWE-bench Multilingual
71.7%SR
BrowseCompOpenAI (2025)
58.3%SR
Terminal-Bench 2.0Stanford × Laude Institute (2026)
38.5%SR
Terminal-Bench
30.5%SR
Humanity's Last Exam
22.1%SR
AA Evaluation Indices
(Artificial Analysis)No AA evaluation data available
LLM Stats Category Scores
(LLM Stats (zeroeval))Creativity90
Writing90
Language80
Legal80
Physics80
Finance80
Healthcare80
Biology80
Chemistry80
Math70
Reasoning70
Frontend Development70
General70
Search60
Structured Output60
Tool Calling60
Long Context50
Agents50
Code50
Vision20
Pricing
No pricing data available
Speed
No speed data available
Provider Price Ranking
Provider Price Ranking
1 providers
ProviderInputOutput
1Qiniu
$0.1
$0.3
Compare pricing across different API providers for this model.