MiniMax-M2.5
MiniMaxMiniMaxOpen WeightMIT · Uso Comercial
Descripción
MiniMax M2.5 is the world's first production-level model designed natively for Agent scenarios. Building on the M2.1 foundation, M2.5 delivers significant improvements in programming, tool calling, search, and office productivity. With only 10B activation parameters from its 230B MoE architecture, it achieves competitive performance against top international models like Claude Opus 4.6 while maintaining high throughput and efficient inference. M2.5 supports full-stack development for PC, App, and cross-platform applications, and excels in agentic workflows including automated customer support, data-analysis pipelines, and complex task execution.
Fecha de lanzamiento
2026-02-12
Parámetros
230.0B
Longitud del contexto
205K
Modalidades
image, text
Radar de capacidades
31
general
43
coding
85
reasoning
57
science
70
agents
60
multimodal
Rankings
| Dominio | #Posición | Puntuación | Fuente |
|---|---|---|---|
| Capacidad agéntica | 69 | 47.0 | LS |
| Ranking de codificación | 118 | 70.0 | AA |
| Ranking general | 94 | 72.0 | AA |
| Ciencia | 129 | 65.0 | AA |
Puntuaciones de benchmarks (LLM Stats)
(LLM Stats (zeroeval))Agents
BrowseCompOpenAI (2025)
76.3%Aut.
MEWC
74.4%Aut.
SWE-Bench ProPrinceton NLP (2024)
55.4%Aut.
VIBE-Pro
54.2%Aut.
Code
SWE-Bench Verified
80.2%Aut.
Multi-SWE-Bench
51.3%Aut.
Finance
GDPval-MM
59.0%Aut.
General
BFCL_v3_MultiTurn
76.8%Aut.
Índices de evaluación AA
(Artificial Analysis)Intelligence Index(Artificial Analysis)34.5
Tau2(Sierra + U Toronto + Vector Institute (2025))1.0
Gpqa(NYU + Cohere + Anthropic (2023))0.8
Lcr(Artificial Analysis)0.7
Ifbench(Google Research (2023))0.7
Scicode(UIUC + Argonne National Lab (2024))0.4
Terminalbench Hard(Stanford × Laude Institute (2026))0.3
Hle(Center for AI Safety + Scale AI (2025))0.2
Puntuaciones por categoría LLM Stats
(LLM Stats (zeroeval))Search80
Frontend Development80
Agents70
Multimodal60
Reasoning60
Finance60
General60
Code60
Precios
Precio de entrada$0.3 / 1M tokens
Precio de salida$1.2 / 1M tokens
Precio mixto (3:1)$0.525 / 1M tokens
Precio de lectura caché$0.03 / 1M tokens
Precio de escritura caché$0.375 / 1M tokens
Velocidad
Tokens/seg0.0
Retraso del primer token0.00s
Tiempo hasta la respuesta0.00s
Ranking de Precios por Proveedor
Ranking de Precios por Proveedor
15 proveedores
Más barato: MiniMaxMás caro: TensorX
ProveedorEntradaSalida
1MiniMaxMás barato
$0
$0
2OpenRouter
$0.22
$0.9
3NanoGPT
$0.3
$1.2
4Alibaba (China)
$0.3
$1.2
5ZenMux
$0.3
$1.2
6NovitaAI
$0.3
$1.2
7Kilo Gateway
$0.3
$1.2
8FrogBot
$0.3
$1.2
9Vercel AI Gateway
$0.3
$1.2
10MiniMax (minimax.io)
$0.3
$1.2
11HPC-AI
$0.3
$1.2
12MiniMax (minimaxi.com)
$0.3
$1.2
13OrcaRouter
$0.3
$1.2
14Merge Gateway
$0.3
$1.2
15TensorX
$0.3
$1.2
Comparar precios entre diferentes proveedores de API para este modelo.