跳轉到主要內容

MiMo-V2.5-Pro

Xiaomi開源權重MIT · 商用許可

描述

MiMo-V2.5-Pro is Xiaomi's 1.02T-parameter sparse Mixture-of-Experts language model with 42B active parameters and a 1M-token context window. It inherits the MiMo-V2-Flash hybrid-attention and Multi-Token Prediction design, extends context during pre-training up to 1M tokens, and uses supervised fine-tuning, domain-specialized reinforcement learning, and Multi-Teacher On-Policy Distillation to improve complex software engineering, long-horizon agentic tasks, and ultra-long-context coherence.

發布日期
2026-04-22
參數規模
1.0T
上下文長度
1.0M
支援模態
text

能力雷達圖

41
general
59
coding
87
reasoning
64
science
70
agents
0
multimodal

排行榜排名

領域#排名分數來源
智慧體能力模型榜52
52.0
LS
程式碼能力榜64
78.0
AA
通用能力榜41
81.0
AA
科學能力56
79.0
AA

基準測試分數 (LLM Stats)

(LLM Stats (zeroeval))

Agents

FrontierSWE (Impl.)340.0%自報
MiMo Coding Bench73.7%自報
TAU3-Bench72.9%自報
Terminal-Bench 2.0Stanford × Laude Institute (2026)68.4%自報
Claw-Eval64.0%自報
SWE-Bench ProPrinceton NLP (2024)57.2%自報
WildClawBench43.0%自報
Finance Agent v241.5%

Biology

GPQANYU + Cohere + Anthropic (2023)66.7%自報

Code

SWE-Bench Verified78.9%自報

Finance

MMLU89.4%自報
MMLU-Pro68.5%自報

General

ARC-C97.2%自報
MMLU-Redux92.8%自報
C-Eval91.5%自報
CMMLU90.2%自報
Global-MMLU83.6%自報
TriviaQA81.3%自報
MBPP+74.1%自報
LiveCodeBench v639.6%自報
SWE-bench Verified (Agentless)35.7%自報

Language

BBH88.4%自報
Winogrande85.6%自報

Long Context

GraphWalks62.0%自報

Math

GSM8k99.6%自報
DROP86.3%自報
MATH86.2%自報
AIMEMAA37.3%自報
Humanity's Last Exam34.0%自報

Reasoning

HellaSwagAI2 (2019)89.8%自報
HumanEval+75.6%自報

AA 評測指數

(Artificial Analysis)
Coding Index(Artificial Analysis)
60.2
Intelligence Index(Artificial Analysis)
42.9
Tau2(Sierra + U Toronto + Vector Institute (2025))
0.9
Gpqa(NYU + Cohere + Anthropic (2023))
0.9
Ifbench(Google Research (2023))
0.8
Lcr(Artificial Analysis)
0.8
Terminalbench V2 1
0.7
Scicode(UIUC + Argonne National Lab (2024))
0.5
Terminalbench Hard(Stanford × Laude Institute (2026))
0.4
Hle(Center for AI Safety + Scale AI (2025))
0.4
Tau Banking
0.1

LLM Stats 分類評分

(LLM Stats (zeroeval))
Language
90
Legal
80
Math
80
Reasoning
80
Frontend Development
80
Healthcare
80
Physics
70
Finance
70
General
70
Biology
70
Chemistry
70
Code
70
Tool Calling
70
Long Context
60
Agents
60
Coding
40
Vision
30

定價

輸入價格$0.435 / 1M tokens
輸出價格$0.87 / 1M tokens
混合價格(3:1)$0.544 / 1M tokens
快取讀取價格$0.0036 / 1M tokens

速度

Tokens/秒48.1
首Token延遲2.82s
首回答延遲44.40s

供應商價格排行

供應商價格排行

8 個供應商

最便宜: Xiaomi最貴: EmpirioLabs AI
供應商輸入輸出
1Xiaomi最便宜
$0
$0
2DeepInfra
$0
$0
3Novita
$0
$0.00001
4DigitalOcean
$0.4
$1.5
5CrofAI
$0.4
$0.8
6OpenCode Go
$0.435
$0.87
7LLM Gateway
$0.435
$0.87
8EmpirioLabs AI
$2.175
$4.35

比較該模型在不同 API 供應商之間的定價。

外部連結