MiMo-V2.6-Pro

XiaomiOpen WeightMIT · Uso Comercial

Descripción

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.

Fecha de lanzamiento

2026-09-21

Parámetros

1.0T

Longitud del contexto

1.0M

Modalidades

audio, image, text, video

Radar de capacidades

general

coding

100

reasoning

scienceest.

agents

multimodal

Science se estima a partir de las puntuaciones científicas de LLM Stats o del razonamiento cuando no hay benchmarks científicos dedicados.

Rankings

Dominio	#Posición	Puntuación	Fuente
Capacidad agéntica	74	47.0	LS
Ranking de codificación	30	82.0	LB
Ranking general	28	45.0	AA
Ranking multimodal	35	60.0	LS
Razonamiento	40	80.0	LB
Ciencia	32	43.0	AA

Puntuaciones de benchmarks (LLM Stats)

(LLM Stats (zeroeval))

Agents

Toolathlon-Verified

76.9%Aut.

SEC-bench Pro

66.3%Aut.

JobBench

62.0%Aut.

AutomationBench v1.0.6

53.1%Aut.

Agents' Last Exam

31.6%Aut.

Program Bench

26.5%Aut.

ExploitGym

17.8%Aut.

Code

CyberGym

94.0%Aut.

MiMo Cyber Bench

81.7%Aut.

MiMo Visual Coding

72.3%Aut.

DeepSWE 1.1

71.9%Aut.

MiMo Coding Bench

63.2%Aut.

ExploitBench

47.9%Aut.

General

GDPval-AA 2.1

1673.00 / 3000Aut.

AA Intelligence Index v4.3

46.3%Aut.

Multimodal

OSWorld-Verified

82.0%Aut.

Reasoning

Terminal-Bench 2.1

89.9%Aut.

Terminal-Bench 4.0

34.9%Aut.

Índices de evaluación AA

(Artificial Analysis)

Strategy And Ops

46.9

Finance And Accounting

38.9

Economics

36.1

Healthcare And Medical

35.8

Legal

35.0

Engineering(Artificial Analysis)

34.3

Intelligence Index(Artificial Analysis)

29.9

Puntuaciones por categoría LLM Stats

(LLM Stats (zeroeval))

Reasoning

100

Agents

100

General

100

Multimodal

Vision

Knowledge

Productivity

Safety

Code

Tool Calling

Precios

Precio de entrada$0.435 / 1M tokens

Precio de salida$0.87 / 1M tokens

Precio mixto (3:1)$0.54375 / 1M tokens

Precio de lectura caché$0.0036 / 1M tokens

Velocidad

Tokens/seg64.9

Retraso del primer token2.90s

Tiempo hasta la respuesta33.70s

Ranking de Precios por Proveedor

18 proveedores

Más barato: RequestyMás caro: Neuralwatt

ProveedorEntradaSalida

1RequestyMás barato

$0.43

$0.87

2Standard Compute

$0.43

$0.87

3XiaomiPRINCIPAL

$0.435

$0.87

4NanoGPT

$0.435

$0.87

5OpenRouter

$0.435

$0.87

6OpenCode Go

$0.435

$0.87

7ZenMux

$0.435

$0.87

8Kilo Gateway

$0.435

$0.87

9Ollama Cloud

$0.435

$0.87

10Vercel AI Gateway

$0.435

$0.87

11DevPass (LLM Gateway)

$0.435

$0.87

12EmpirioLabs AI

$0.435

$0.87

13LLM Gateway

$0.435

$0.87

14Boundless

$0.435

$0.87

15CrossModel

$0.47

$0.94

16AIHubMix

$0.48

$0.96

17above.dev

$0.5077

$1.0154

18Neuralwatt

$0.87

$1.74

Comparar precios entre diferentes proveedores de API para este modelo.

Fuentes externas

LLM Stats Artificial Analysis