Saltar al contenido principal

Qwen3 VL 4B (Reasoning)

AlibabaQwenOpen WeightApache 2.0 · Uso Comercial

Descripción

Qwen3-VL is a large multimodal model that unifies vision, language, and reasoning to achieve human-level perception and cognition across text, images, and video. Built on a 235B-parameter architecture, it integrates early joint training of visual and textual modalities for strong language grounding. The model supports up to a 1 million-token context window and excels at visual understanding, spatial reasoning, long video comprehension, and tool-based interaction. It can generate code from images, perform precise 2D/3D object grounding, and operate digital interfaces like a visual agent. The “Instruct” version rivals Gemini 2.5 Pro in perception benchmarks, while the “Thinking” version leads in multimodal reasoning and STEM tasks. With multilingual OCR, creative writing, and fine-grained scene interpretation, Qwen3-VL establishes a new open-source frontier for integrated vision-language intelligence.

Fecha de lanzamiento
2025-10-14
Parámetros
4.0B
Longitud del contexto
—
Modalidades
image, text

Radar de capacidades

26
general
32
coding
30
reasoning
36
science
70
agents
100
multimodal

Rankings

Dominio#PosiciónPuntuaciónFuente
Ranking de codificación508
20.0
AA
Ranking general500
28.0
AA
Ranking multimodal140
25.0
LS
Ciencia515
26.0
AA

Puntuaciones de benchmarks (LLM Stats)

(LLM Stats (zeroeval))

Chat

MM-MT-Bench7.70 / 100Aut.
IFEvalGoogle Research (2023)82.6%Aut.
Multi-IF73.6%Aut.

Creativity

Creative Writing v376.1%Aut.

General

MMLU81.5%Aut.
MLVU-M75.7%Aut.
BFCL-v367.3%Aut.
Include64.6%Aut.
Arena-Hard v236.8%Aut.

Language

MMLU-Redux86.0%Aut.
MMLU-Pro73.6%Aut.
MMLU-ProX65.0%Aut.

Math

MathVista-Mini79.5%Aut.
AIME 202574.5%Aut.
LiveBench 2024112568.4%Aut.
MathVision60.0%Aut.
HMMT2553.1%Aut.
PolyMATH44.6%Aut.

Multimodal

VideoMMMU69.4%Aut.
OSWorld31.4%Aut.

Reasoning

CharXiv-D83.9%Aut.
GPQANYU + Cohere + Anthropic (2023)64.1%Aut.
LiveCodeBench v651.3%Aut.
CharXiv-R50.3%Aut.
SuperGPQA46.8%Aut.

Video

CharadesSTA59.0%Aut.

Vision

DocVQAtest94.2%Aut.
ScreenSpot92.9%Aut.
MMBench-V1.186.7%Aut.
AI2D84.9%Aut.
InfoVQAtest83.0%Aut.
OCRBench80.8%Aut.
MuirBench75.0%Aut.
CC-OCR73.8%Aut.
MMStar73.2%Aut.
RealWorldQA73.2%Aut.
MMMU (val)70.8%Aut.
MVBench69.3%Aut.
Hallusion Bench64.1%Aut.
BLINK63.4%Aut.
OCRBench-V2 (en)61.8%Aut.
MMMU-Pro57.0%Aut.
OCRBench-V2 (zh)55.8%Aut.
LVBench53.5%Aut.
ScreenSpot Pro49.2%Aut.
ERQA47.3%Aut.
ODinW39.4%Aut.

Writing

WritingBench84.0%Aut.

Índices de evaluación AA

(Artificial Analysis)
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))
70.0
Gpqa(NYU + Cohere + Anthropic (2023))
49.4
Ifbench(Google Research (2023))
36.6
Livecodebench(UC Berkeley + MIT + Cornell (2024))
32.0
Math Index(Artificial Analysis)
25.7
Aime 25(MAA (Mathematical Association of America))
25.7
Lcr(Artificial Analysis)
21.3
Tau2(Sierra + U Toronto + Vector Institute (2025))
15.5
Intelligence Index(Artificial Analysis)
7.0
Hle(Center for AI Safety + Scale AI (2025))
4.6
Terminalbench Hard(Stanford × Laude Institute (2026))
1.5

Puntuaciones por categoría LLM Stats

(LLM Stats (zeroeval))
Chat
3
Communication
3
Multimodal
100
Instruction Following
80
Structured Output
80
General
80
Image To Text
70
Language
70
Legal
70
Math
70
Reasoning
70
Finance
70
Grounding
70
Healthcare
70
Creativity
70
Text-to-image
70
Tool Calling
70
Vision
70
Writing
70
Physics
60
Spatial Reasoning
60
3d
60
Biology
60
Chemistry
60
Video
60
Long Context
50
Agents
50
Economics
50

Precios

Precio de entradaGratis
Precio de salidaGratis
Precio mixto (3:1)Gratis

Velocidad

Tokens/seg0.0
Retraso del primer token0.00s
Tiempo hasta la respuesta0.00s

Ranking de Precios por Proveedor

No hay datos de proveedores disponibles

Fuentes externas