跳轉到主要內容

Qwen3 VL 4B Instruct

AlibabaQwen開源權重Apache 2.0 · 商用許可

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.

發布日期
2025-10-14
參數規模
4.0B
上下文長度
—
支援模態
image, text

能力雷達圖

23
general
29
coding
37
reasoning
27
science
60
agents
90
multimodal

排行榜排名

領域#排名分數來源
程式碼能力榜545
16.0
AA
通用能力榜532
26.0
AA
多模態榜139
26.0
LS
科學能力589
18.0
AA

基準測試分數 (LLM Stats)

(LLM Stats (zeroeval))

Chat

MM-MT-Bench7.50 / 100自報
IFEvalGoogle Research (2023)82.3%自報

Factuality

SimpleQA48.0%自報

General

MMLU77.2%自報
MLVU-M75.3%自報
BFCL-v363.3%自報
Include61.4%自報

Language

MMLU-Redux81.5%自報
MMLU-Pro67.1%自報
MMLU-ProX59.4%自報

Math

MathVista-Mini73.7%自報
LiveBench 2024112560.9%自報
MathVision51.6%自報
AIME 202546.6%自報
HMMT2530.7%自報
PolyMATH28.8%自報

Multimodal

VideoMMMU56.2%自報
OSWorld26.2%自報

Reasoning

CharXiv-D76.2%自報
SuperGPQA40.3%自報
CharXiv-R39.7%自報
LiveCodeBench v637.9%自報

Video

CharadesSTA55.5%自報

Vision

DocVQAtest95.3%自報
ScreenSpot94.0%自報
OCRBench88.1%自報
MMBench-V1.185.1%自報
AI2D84.1%自報
InfoVQAtest80.3%自報
CC-OCR76.2%自報
RealWorldQA70.9%自報
MMStar69.8%自報
MVBench68.9%自報
MMMU (val)67.4%自報
BLINK65.8%自報
MuirBench63.8%自報
OCRBench-V2 (en)63.7%自報
ScreenSpot Pro59.5%自報
OCRBench-V2 (zh)57.6%自報
Hallusion Bench57.6%自報
LVBench56.2%自報
MMMU-Pro53.2%自報
ODinW48.2%自報
ERQA41.3%自報

Writing

WritingBench82.5%自報

AA 評測指數

(Artificial Analysis)
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))
63.4
Gpqa(NYU + Cohere + Anthropic (2023))
37.1
Math Index(Artificial Analysis)
37.0
Aime 25(MAA (Mathematical Association of America))
37.0
Ifbench(Google Research (2023))
31.8
Livecodebench(UC Berkeley + MIT + Cornell (2024))
29.0
Tau2(Sierra + U Toronto + Vector Institute (2025))
23.4
Lcr(Artificial Analysis)
14.0
Intelligence Index(Artificial Analysis)
5.7
Hle(Center for AI Safety + Scale AI (2025))
3.6
Terminalbench Hard(Stanford × Laude Institute (2026))
0.0

LLM Stats 分類評分

(LLM Stats (zeroeval))
Chat
4
Communication
4
Multimodal
90
Instruction Following
80
General
80
Grounding
80
Creativity
80
Text-to-image
80
Writing
80
Image To Text
70
Language
70
Legal
70
Structured Output
70
3d
70
Long Context
60
Math
60
Reasoning
60
Spatial Reasoning
60
Finance
60
Healthcare
60
Tool Calling
60
Video
60
Vision
60
Factuality
50
Physics
40
Agents
40
Chemistry
40
Economics
40

定價

輸入價格免費
輸出價格免費
混合價格(3:1)免費

速度

Tokens/秒0.0
首Token延遲0.00s
首回答延遲0.00s

供應商價格排行

暫無提供商資料

外部連結