跳轉到主要內容

MiMo-V2.5-Pro (Reasoning)

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
audio, text

能力雷達圖

70
general
70
coding
80
reasoning
60
science估算
70
agents
30
multimodal

缺少專門科學評測時,Science 由 LLM Stats 科學得分或推理能力估算。

排行榜排名

領域#排名分數來源
智慧體能力模型榜69
48.0
LS

基準測試分數 (LLM Stats)

(LLM Stats (zeroeval))

Agents

TAU3-Bench72.9%自報
WildClawBench43.0%自報
Finance Agent v241.5%

Code

FrontierSWE (Impl.)340.0%自報
MiMo Coding Bench73.7%自報
Claw-Eval64.0%自報

General

C-Eval91.5%自報
MMLU89.4%自報
Global-MMLU83.6%自報
TriviaQA81.3%自報
SWE-bench Verified (Agentless)35.7%自報

Language

MMLU-Redux92.8%自報
CMMLU90.2%自報
MMLU-Pro68.5%自報

Long Context

GraphWalks62.0%自報

Math

GSM8k99.6%自報
MATH86.2%自報
AIMEMAA37.3%自報

Reasoning

ARC-C97.2%自報
HellaSwagAI2 (2019)89.8%自報
BBH88.4%自報
DROP86.3%自報
Winogrande85.6%自報
SWE-Bench Verified78.9%自報
HumanEval+75.6%自報
MBPP+74.1%自報
Terminal-Bench 2.0Stanford × Laude Institute (2026)68.4%自報
GPQANYU + Cohere + Anthropic (2023)66.7%自報
SWE-Bench ProPrinceton NLP (2024)57.2%自報
LiveCodeBench v639.6%自報
Humanity's Last Exam34.0%自報

AA 評測指數

(Artificial Analysis)

暫無 AA 評測資料

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$0.348 / 1M tokens
輸出價格$0.696 / 1M tokens
混合價格(3:1)$0.54375 / 1M tokens
快取讀取價格$0.0036 / 1M tokens

速度

暫無速度資料

供應商價格排行

供應商價格排行

3 個供應商

最便宜: Xiaomi最貴: Novita
供應商輸入輸出
1Xiaomi主要
$0.348
$0.696
2DeepInfra
$1
$3
3Novita
$2
$6

比較該模型在不同 API 供應商之間的定價。

外部連結