Qwen2.5 VL 72B Instruct
Alibaba Cloud / Qwen TeamQwenOpen Weighttongyi-qianwen
Descripción
Qwen2.5-VL is the new flagship vision-language model of Qwen, significantly improved from Qwen2-VL. It excels at recognizing objects, analyzing text/charts/layouts in images, acting as a visual agent, understanding long videos (over 1 hour) with event pinpointing, performing visual localization (bounding boxes/points), and generating structured outputs from documents.
Fecha de lanzamiento
2025-01-26
Parámetros
72.0B
Longitud del contexto
131K
Modalidades
image, text
Radar de capacidades
50
general
0
coding
60
reasoning
60
scienceest.
40
agents
80
multimodal
Science usa un proxy de razonamiento cuando los benchmarks científicos dedicados no están disponibles.
Rankings
| Dominio | #Posición | Puntuación | Fuente |
|---|---|---|---|
| Capacidad agéntica | 98 | 45.0 | LS |
| Ranking multimodal | 59 | 73.0 | LS |
| Razonamiento | 79 | 55.0 | LS |
Puntuaciones de benchmarks (LLM Stats)
Agents
AITZ_EM
83.2%Aut.
MobileMiniWob++_SR
68.0%Aut.
AndroidWorld_SR
35.0%Aut.
OSWorld
8.8%Aut.
General
MMVet
76.2%Aut.
MLVU-M
74.6%Aut.
MMStar
70.8%Aut.
MMMU
70.2%Aut.
MMMU-Pro
51.1%Aut.
Grounding
ScreenSpot
87.1%Aut.
ScreenSpot Pro
43.6%Aut.
Image To Text
DocVQA
96.4%Aut.
OCRBench
88.5%Aut.
OCRBench-V2 (en)
61.5%Aut.
Long Context
EgoSchema
76.2%Aut.
LVBench
47.3%Aut.
Math
MathVista-Mini
74.8%Aut.
MathVision
38.1%Aut.
Multimodal
Android Control Low_EM
93.7%Aut.
ChartQA
89.5%Aut.
AI2D
88.4%Aut.
MMBench
88.0%Aut.
CC-OCR
79.8%Aut.
TempCompass
74.8%Aut.
VideoMME w/o sub.
73.3%Aut.
PerceptionTest
73.2%Aut.
MVBench
70.4%Aut.
Android Control High_EM
67.4%Aut.
MMBench-Video
2.0%Aut.
Reasoning
Hallusion Bench
55.2%Aut.
Índices de evaluación AA
No hay datos de evaluación AA disponibles
Puntuaciones por categoría LLM Stats
Image To Text80
Structured Output80
Text-to-image80
Reasoning70
Spatial Reasoning70
Grounding70
Healthcare70
Long Context60
Math60
Multimodal60
Vision60
General50
Video50
Agents40
Precios
Precio de entrada$2.8 / 1M tokens
Precio de salida$8.4 / 1M tokens
Precio mixto (3:1)$4.2 / 1M tokens
Velocidad
No hay datos de velocidad disponibles
Ranking de Precios por Proveedor
Ranking de Precios por Proveedor
12 proveedores
Más barato: Nebius Token FactoryMás caro: LLM Gateway
ProveedorEntradaSalida
1Nebius Token FactoryMás barato
$0.25
$0.75
2SiliconFlow (China)
$0.59
$0.59
3SiliconFlow
$0.59
$0.59
4NanoGPT
$0.69989
$0.69989
5OpenRouter
$0.8
$1
6NovitaAI
$0.8
$0.8
7Kilo Gateway
$0.8
$0.8
8OVHcloud AI Endpoints
$1.01
$1.01
9Alibaba (China)
$2.294
$6.881
10Alibaba Cloud / Qwen TeamPRINCIPAL
$2.8
$8.4
11Alibaba
$2.8
$8.4
12LLM Gateway
$2.8
$8.4
Comparar precios entre diferentes proveedores de API para este modelo.