Skip to main content

Qwen3 VL 4B (Reasoning)

AlibabaQwenOpen WeightApache 2.0 · Commercial OK

Description

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.

Release Date
2025-10-14
Parameters
4.0B
Context Length
Modalities
image, text

Capability Radar

26
general
29
coding
30
reasoning
29
scienceest.
70
agents
100
multimodal

Science uses a reasoning proxy when dedicated science benchmarks are unavailable.

Rankings

Domain#RankScoreSource
Agentic Capability74
53.0
LS
Code Ranking351
22.0
AA
General Ranking375
30.0
AA
Math Reasoning285
26.0
AA
Multimodal Ranking56
74.0
LS
Reasoning82
54.0
LS
Science402
27.0
AA

Benchmark Scores (LLM Stats)

3d

BLINK63.4%SR

Agents

BFCL-v367.3%SR
OSWorld31.4%SR

Biology

GPQA64.1%SR

Chemistry

SuperGPQA46.8%SR

Communication

MM-MT-Bench7.70 / 100SR
WritingBench84.0%SR
Multi-IF73.6%SR

Creativity

Creative Writing v376.1%SR
Arena-Hard v236.8%SR

Finance

MMLU81.5%SR
MMLU-Pro73.6%SR
MMLU-ProX65.0%SR

General

MMLU-Redux86.0%SR
IFEval82.6%SR
MLVU-M75.7%SR
MMStar73.2%SR
MMMU (val)70.8%SR
LiveBench 2024112568.4%SR
Include64.6%SR
MMMU-Pro57.0%SR
LiveCodeBench v651.3%SR

Grounding

ScreenSpot92.9%SR
ScreenSpot Pro49.2%SR

Healthcare

VideoMMMU69.4%SR

Image To Text

OCRBench80.8%SR
OCRBench-V2 (en)61.8%SR
OCRBench-V2 (zh)55.8%SR

Language

CharadesSTA59.0%SR

Long Context

LVBench53.5%SR

Math

MathVista-Mini79.5%SR
AIME 202574.5%SR
MathVision60.0%SR
HMMT2553.1%SR
PolyMATH44.6%SR

Multimodal

DocVQAtest94.2%SR
MMBench-V1.186.7%SR
AI2D84.9%SR
CharXiv-D83.9%SR
InfoVQAtest83.0%SR
MuirBench75.0%SR
CC-OCR73.8%SR
MVBench69.3%SR
CharXiv-R50.3%SR

Reasoning

Hallusion Bench64.1%SR
ERQA47.3%SR

Spatial Reasoning

RealWorldQA73.2%SR

Vision

ODinW39.4%SR

AA Evaluation Indices

Math Index
25.7
Intelligence Index
7.9
Mmlu Pro
0.7
Gpqa
0.5
Ifbench
0.4
Livecodebench
0.3
Aime 25
0.3
Lcr
0.2
Scicode
0.2
Tau2
0.2
Hle
0.0
Terminalbench Hard
0.0

LLM Stats Category Scores

Communication
3
Multimodal
100
Instruction Following
80
Structured Output
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
General
60
3d
60
Biology
60
Chemistry
60
Video
60
Long Context
50
Agents
50
Economics
50

Pricing

Input PriceFree
Output PriceFree
Blended Price (3:1)Free

Speed

Tokens/sec0.0
Time to First Token0.00s
Time to Answer0.00s

Provider Price Ranking

Provider Price Ranking

1 providers

ProviderInputOutput
1DeepInfra
$0
$0

Compare pricing across different API providers for this model.

External Sources