Saltar al contenido principal

MiMo-V2.6-Flash

XiaomiOpen WeightMIT · Uso Comercial

Descripción

MiMo-V2.6-Flash is Xiaomi's MIT-licensed omnimodal sparse Mixture-of-Experts model with 309B total parameters and 15B 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-Flash-RL. Benchmark results are Xiaomi-reported release evaluations, distinct from intermediate live-training checkpoints.

Fecha de lanzamiento
2026-09-21
Parámetros
309.0B
Longitud del contexto
1.0M
Modalidades
audio, image, text, video

Radar de capacidades

37
general
51
coding
50
reasoning
45
science
50
agents
80
multimodal

Rankings

Dominio#PosiciónPuntuaciónFuente
Capacidad agéntica105
28.0
LS
Ranking de codificación98
84.0
AA
Ranking general119
64.0
AA
Ranking multimodal57
56.0
LS
Ciencia159
65.0
AA

Puntuaciones de benchmarks (LLM Stats)

(LLM Stats (zeroeval))

Agents

Toolathlon-Verified73.6%Aut.
JobBench61.2%Aut.
AutomationBench v1.0.652.3%Aut.
SEC-bench Pro47.5%Aut.
Agents' Last Exam27.6%Aut.
Program Bench26.0%Aut.
ExploitGym6.0%Aut.

Code

CyberGym95.1%Aut.
MiMo Cyber Bench77.2%Aut.
MiMo Visual Coding71.5%Aut.
DeepSWE 1.167.9%Aut.
MiMo Coding Bench61.2%Aut.
ExploitBench25.3%Aut.

Multimodal

OSWorld-Verified80.8%Aut.

Reasoning

Terminal-Bench 2.187.6%Aut.
Terminal-Bench 4.028.8%Aut.

Índices de evaluación AA

(Artificial Analysis)
Lcr(Artificial Analysis)
74.3
Scicode(UIUC + Argonne National Lab (2024))
51.3
Intelligence Index(Artificial Analysis)
37.9
Hle(Center for AI Safety + Scale AI (2025))
35.1

Puntuaciones por categoría LLM Stats

(LLM Stats (zeroeval))
Multimodal
80
Vision
80
Reasoning
50
General
50
Agents
50
Code
50
Tool Calling
50
Safety
40

Precios

Precio de entrada$0.14 / 1M tokens
Precio de salida$0.28 / 1M tokens
Precio mixto (3:1)$0.175 / 1M tokens
Precio de lectura caché$0.0028 / 1M tokens

Velocidad

Tokens/seg47.5
Retraso del primer token4.07s
Tiempo hasta la respuesta46.20s

Ranking de Precios por Proveedor

Ranking de Precios por Proveedor

13 proveedores

Más barato: XiaomiMás caro: above.dev
ProveedorEntradaSalida
1XiaomiMás barato
$0
$0
2Kilo Gateway
$0.08
$1.28
3NanoGPT
$0.14
$0.28
4OpenRouter
$0.14
$0.28
5OpenCode Go
$0.14
$0.28
6Requesty
$0.14
$0.28
7Vercel AI Gateway
$0.14
$0.28
8DevPass (LLM Gateway)
$0.14
$0.28
9EmpirioLabs AI
$0.14
$0.28
10LLM Gateway
$0.14
$0.28
11AIHubMix
$0.155
$0.31
12CrossModel
$0.16
$0.32
13above.dev
$0.1692
$0.3385

Comparar precios entre diferentes proveedores de API para este modelo.

Fuentes externas