Saltar al contenido principal
AITier

MiMo-V2.5-Pro

XiaomiOpen WeightMIT · Uso Comercial

Descripción

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.

Fecha de lanzamiento
2026-04-22
Parámetros
1.0T
Longitud del contexto
1.0M
Modalidades
text

Radar de capacidades

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

Rankings

Dominio#PosiciónPuntuaciónFuente
Capacidad agéntica52
52.0
LS
Ranking de codificación64
78.0
AA
Ranking general41
81.0
AA
Ciencia56
79.0
AA

Puntuaciones de benchmarks (LLM Stats)

(LLM Stats (zeroeval))

Agents

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

Biology

GPQANYU + Cohere + Anthropic (2023)66.7%Aut.

Code

SWE-Bench Verified78.9%Aut.

Finance

MMLU89.4%Aut.
MMLU-Pro68.5%Aut.

General

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

Language

BBH88.4%Aut.
Winogrande85.6%Aut.

Long Context

GraphWalks62.0%Aut.

Math

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

Reasoning

HellaSwagAI2 (2019)89.8%Aut.
HumanEval+75.6%Aut.

Índices de evaluación AA

(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

Puntuaciones por categoría LLM Stats

(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

Precios

Precio de entrada$0.435 / 1M tokens
Precio de salida$0.87 / 1M tokens
Precio mixto (3:1)$0.544 / 1M tokens
Precio de lectura caché$0.0036 / 1M tokens

Velocidad

Tokens/seg48.1
Retraso del primer token2.82s
Tiempo hasta la respuesta44.40s

Ranking de Precios por Proveedor

Ranking de Precios por Proveedor

8 proveedores

Más barato: XiaomiMás caro: EmpirioLabs AI
ProveedorEntradaSalida
1XiaomiMás barato
$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

Comparar precios entre diferentes proveedores de API para este modelo.

Fuentes externas

LLM StatsArtificial Analysis