MiMo-V2-Pro
XiaomiProprietary
Descripción
MiMo-V2-Pro is Xiaomi's flagship foundation model built for real-world agentic workloads. A Mixture-of-Experts model with over 1T total parameters and 42B active, roughly 3x larger than MiMo-V2-Flash. Inherits the Hybrid Attention mechanism with a 7:1 ratio and supports up to 1M-token context. Optimized for coding and agent tasks through post-training scaling across diverse agent scenarios, with native support for complex tool calling and multi-step reasoning.
Fecha de lanzamiento
2026-03-18
Parámetros
1.0T
Longitud del contexto
1.0M
Modalidades
text
Radar de capacidades
45
general
42
coding
87
reasoning
60
scienceest.
80
agents
0
multimodal
Science usa un proxy de razonamiento cuando los benchmarks científicos dedicados no están disponibles.
Rankings
| Dominio | #Posición | Puntuación | Fuente |
|---|---|---|---|
| Agents & Tools | 32 | 63.0 | LS |
| Code Ranking | 53 | 72.0 | AA |
| General Ranking | 30 | 84.0 | AA |
| Science | 38 | 75.0 | AA |
Puntuaciones de benchmarks (LLM Stats)
Agents
GDPval-AA
1426.00 / 3000Aut.
DeepSearchQA
86.7%Aut.
PinchBench
81.0%Aut.
Claw-Eval
61.5%Aut.
Terminal-Bench 2.0
57.1%Aut.
Code
SWE-Bench Verified
78.0%Aut.
SWE-bench Multilingual
71.7%Aut.
Communication
Tau2 Telecom
96.8%Aut.
Índices de evaluación AA
Intelligence Index49.2
Coding Index41.4
Tau20.9
Gpqa0.9
Ifbench0.7
Lcr0.6
Scicode0.4
Terminalbench Hard0.4
Hle0.3
Puntuaciones por categoría LLM Stats
Finance100
General100
Legal100
Agents100
Reasoning100
Communication100
Search90
Tool Calling80
Frontend Development80
Code70
Coding70
Precios
Precio de entrada$1 / 1M tokens
Precio de salida$3 / 1M tokens
Precio mixto (3:1)$1.5 / 1M tokens
Velocidad
Tokens/seg65.2 tokens/s
Retraso del primer token2.11s
Tiempo hasta la respuesta46.98s
Proveedores disponibles
(Unidades internas LS)| Proveedor | Precio de entrada | Precio de salida |
|---|---|---|
| Xiaomi | 1.0M | 3.0M |