跳转到主要内容

MiMo-V2.6-Pro

Xiaomi开源权重MIT · 商用许可

描述

MiMo-V2.6-Pro is Xiaomi's MIT-licensed omnimodal sparse Mixture-of-Experts model with 1.02T total parameters and 42B active parameters. It supports text, image, video, and audio understanding with a 1,048,576-token context window and text output. MiMo-V2.6 scales reinforcement learning across coding, general agents, visual tasks, and cybersecurity. Xiaomi's launch article is dated September 22, 2026; released weights are named MiMo-V2.6-Pro-RL. Benchmark results are Xiaomi-reported release evaluations, distinct from intermediate live-training checkpoints. UltraSpeed serves the same model at higher speed for $4.35 input and $8.70 output per million tokens.

发布日期
2026-09-21
参数规模
1.0T
上下文长度
1.0M
支持模态
audio, image, text, video

能力雷达图

47
general
61
coding
100
reasoning
57
science
60
agents
80
multimodal

排行榜排名

领域#排名分数来源
智能体能力模型榜26
57.0
LS
代码能力榜4
97.0
AA
通用能力榜31
79.0
AA
多模态榜41
59.0
LS
科学能力29
85.0
AA

基准测试分数 (LLM Stats)

(LLM Stats (zeroeval))

Agents

Toolathlon-Verified76.9%自报
SEC-bench Pro66.3%自报
JobBench62.0%自报
AutomationBench v1.0.653.1%自报
Agents' Last Exam31.6%自报
Program Bench26.5%自报
ExploitGym17.8%自报

Code

CyberGym94.0%自报
MiMo Cyber Bench81.7%自报
MiMo Visual Coding72.3%自报
DeepSWE 1.171.9%自报
MiMo Coding Bench63.2%自报
ExploitBench47.9%自报

General

GDPval-AA 2.11673.00 / 3000自报
AA Intelligence Index v4.346.3%自报

Multimodal

OSWorld-Verified82.0%自报

Reasoning

Terminal-Bench 2.189.9%自报
Terminal-Bench 4.034.9%自报

AA 评测指数

(Artificial Analysis)
Lcr(Artificial Analysis)
86.3
Scicode(UIUC + Argonne National Lab (2024))
60.9
Hle(Center for AI Safety + Scale AI (2025))
49.4
Intelligence Index(Artificial Analysis)
46.3
Terminalbench V4 0
34.8

LLM Stats 分类评分

(LLM Stats (zeroeval))
Reasoning
100
General
100
Agents
100
Multimodal
80
Vision
80
Safety
60
Code
60
Tool Calling
60

定价

输入价格$0.435 / 1M tokens
输出价格$0.87 / 1M tokens
混合价格(3:1)$0.544 / 1M tokens
缓存读取价格$0.0036 / 1M tokens

速度

Tokens/秒44.3
首Token延迟2.94s
首回答延迟48.09s

供应商价格排行

供应商价格排行

14 个供应商

最便宜: Xiaomi最贵: above.dev
供应商输入输出
1Xiaomi最便宜
$0
$0
2Kilo Gateway
$0.43
$0.87
3Requesty
$0.43
$0.87
4NanoGPT
$0.435
$0.87
5OpenRouter
$0.435
$0.87
6OpenCode Go
$0.435
$0.87
7ZenMux
$0.435
$0.87
8Vercel AI Gateway
$0.435
$0.87
9DevPass (LLM Gateway)
$0.435
$0.87
10EmpirioLabs AI
$0.435
$0.87
11LLM Gateway
$0.435
$0.87
12CrossModel
$0.47
$0.94
13AIHubMix
$0.48
$0.96
14above.dev
$0.5077
$1.0154

比较该模型在不同 API 供应商之间的定价。

外部链接