跳转到主要内容

Qwen3 VL 4B (Reasoning)

AlibabaQwen开源权重Apache 2.0 · 商用许可

描述

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.

发布日期
2025-10-14
参数规模
4.0B
上下文长度
—
支持模态
image, text

能力雷达图

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

排行榜排名

领域#排名分数来源
代码能力榜508
20.0
AA
通用能力榜500
28.0
AA
多模态榜140
25.0
LS
科学能力515
26.0
AA

基准测试分数 (LLM Stats)

(LLM Stats (zeroeval))

Chat

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

Creativity

Creative Writing v376.1%自报

General

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

Language

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

Math

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

Multimodal

VideoMMMU69.4%自报
OSWorld31.4%自报

Reasoning

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

Video

CharadesSTA59.0%自报

Vision

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

Writing

WritingBench84.0%自报

AA 评测指数

(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

LLM Stats 分类评分

(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

定价

输入价格免费
输出价格免费
混合价格(3:1)免费

速度

Tokens/秒0.0
首Token延迟0.00s
首回答延迟0.00s

供应商价格排行

暂无提供商数据

外部链接