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
基準測試分數 (LLM Stats)
(LLM Stats (zeroeval))Agents
FrontierSWE (Impl.)
340.0%自報
MiMo Coding Bench
73.7%自報
TAU3-Bench
72.9%自報
Terminal-Bench 2.0Stanford × Laude Institute (2026)
68.4%自報
Claw-Eval
64.0%自報
SWE-Bench ProPrinceton NLP (2024)
57.2%自報
WildClawBench
43.0%自報
Finance Agent v2
41.5%
Biology
GPQANYU + Cohere + Anthropic (2023)
66.7%自報
Code
SWE-Bench Verified
78.9%自報
Finance
MMLU
89.4%自報
MMLU-Pro
68.5%自報
General
ARC-C
97.2%自報
MMLU-Redux
92.8%自報
C-Eval
91.5%自報
CMMLU
90.2%自報
Global-MMLU
83.6%自報
TriviaQA
81.3%自報
MBPP+
74.1%自報
LiveCodeBench v6
39.6%自報
SWE-bench Verified (Agentless)
35.7%自報
Language
BBH
88.4%自報
Winogrande
85.6%自報
Long Context
GraphWalks
62.0%自報
Math
GSM8k
99.6%自報
DROP
86.3%自報
MATH
86.2%自報
AIMEMAA
37.3%自報
Humanity's Last Exam
34.0%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 10.7
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 Banking0.1
LLM Stats 分類評分
(LLM Stats (zeroeval))Language90
Legal80
Math80
Reasoning80
Frontend Development80
Healthcare80
Physics70
Finance70
General70
Biology70
Chemistry70
Code70
Tool Calling70
Long Context60
Agents60
Coding40
Vision30
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。