MiMo-V2-Flash (Reasoning)
Xiaomi
描述
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.
发布日期
2025-12-16
参数规模
—
上下文长度
262K
支持模态
text
能力雷达图
46
general
76
coding
94
reasoning
56
science估算
60
agents
0
multimodal
Science 在缺少专门科学评测时使用推理能力代理估算。
排行榜排名
基准测试分数 (LLM Stats)
Agents
Tau-bench
80.3%自报
BrowseComp
58.3%自报
Terminal-Bench 2.0
38.5%自报
Terminal-Bench
30.5%自报
Biology
GPQA
83.7%自报
Code
SWE-Bench Verified
73.4%自报
SWE-bench Multilingual
71.7%自报
Creativity
Arena-Hard v2
86.2%自报
Finance
MMLU-Pro
84.9%自报
General
LiveCodeBench v6
80.6%自报
LongBench v2
60.6%自报
MRCR
45.7%自报
Math
AIME 2025
94.1%自报
HMMT 2025
84.4%自报
Humanity's Last Exam
22.1%自报
AA 评测指数
Math Index96.3
Intelligence Index31.2
Aime 251.0
Tau21.0
Livecodebench0.9
Gpqa0.8
Mmlu Pro0.8
Ifbench0.6
Lcr0.6
Scicode0.4
Terminalbench Hard0.3
Hle0.2
LLM Stats 分类评分
Creativity90
Writing90
Language80
Legal80
Physics80
Finance80
Healthcare80
Biology80
Chemistry80
Math70
Reasoning70
Frontend Development70
General70
Search60
Structured Output60
Tool Calling60
Long Context50
Agents50
Code50
Vision20
定价
输入价格$0.1 / 1M tokens
输出价格$0.3 / 1M tokens
混合价格(3:1)$0.15 / 1M tokens
缓存读取价格$0.01 / 1M tokens
速度
Tokens/秒75.2
首Token延迟2.23s
首回答延迟28.81s
供应商价格排行
供应商价格排行
4 个供应商
最便宜: Xiaomi最贵: NanoGPT
供应商输入输出
1Xiaomi主要
$0.1
$0.3
2Qiniu
$0.1
$0.3
3LLM Gateway
$0.1
$0.3
4NanoGPT
$0.102
$0.306
比较该模型在不同 API 供应商之间的定价。