Skip to main content

Qwen3 VL 30B A3B Instruct

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
2025-10-03
Parameters
31.0B
Context Length
131K
Modalities
image, text, video

Capability Radar

29
general
44
coding
72
reasoning
43
scienceest.
70
agents
100
multimodal

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

Rankings

Domain#RankScoreSource
Agentic Capability80
52.0
LS
Code Ranking289
31.0
AA
General Ranking341
33.0
AA
Math Reasoning110
73.0
AA
Multimodal Ranking50
75.0
LS
Reasoning90
51.0
LS
Science255
44.0
AA

Benchmark Scores (LLM Stats)

3d

BLINK67.7%SR

Agents

BFCL-v366.3%SR
OSWorld30.3%SR

Biology

GPQA70.4%SR

Chemistry

SuperGPQA53.1%SR

Communication

MM-MT-Bench8.10 / 100SR
WritingBench82.6%SR
Multi-IF66.1%SR

Creativity

Creative Writing v384.6%SR
Arena-Hard v258.5%SR

Factuality

SimpleQA27.0%SR

Finance

MMLU85.0%SR
MMLU-Pro77.8%SR
MMLU-ProX70.9%SR

General

MMLU-Redux88.4%SR
IFEval85.8%SR
MLVU-M81.3%SR
MMMU (val)74.2%SR
MMStar72.1%SR
Include71.6%SR
LiveBench 2024112565.4%SR
MMMU-Pro60.4%SR
LiveCodeBench v642.6%SR

Grounding

ScreenSpot94.7%SR
ScreenSpot Pro60.5%SR

Healthcare

VideoMMMU68.7%SR

Image To Text

OCRBench90.3%SR
OCRBench-V2 (en)63.2%SR
OCRBench-V2 (zh)57.8%SR

Language

CharadesSTA63.5%SR

Long Context

LVBench62.5%SR

Math

MathVista-Mini80.1%SR
AIME 202569.3%SR
MathVision60.2%SR
HMMT2550.6%SR
PolyMATH44.3%SR

Multimodal

DocVQAtest95.0%SR
MMBench-V1.187.0%SR
CharXiv-D85.5%SR
AI2D85.0%SR
InfoVQAtest82.0%SR
CC-OCR80.7%SR
Video-MME74.5%SR
MVBench72.3%SR
MuirBench62.9%SR
CharXiv-R48.9%SR

Reasoning

Hallusion Bench61.5%SR
ERQA43.0%SR

Spatial Reasoning

RealWorldQA73.7%SR

Vision

ODinW47.5%SR

AA Evaluation Indices

Math Index
72.3
Intelligence Index
10.0
Mmlu Pro
0.8
Aime 25
0.7
Gpqa
0.7
Livecodebench
0.5
Ifbench
0.3
Scicode
0.3
Lcr
0.2
Tau2
0.2
Hle
0.1
Terminalbench Hard
0.1

LLM Stats Category Scores

Communication
3
Multimodal
100
Instruction Following
80
Language
80
Structured Output
80
Grounding
80
Creativity
80
Text-to-image
80
Writing
80
Image To Text
70
Legal
70
Math
70
Reasoning
70
Spatial Reasoning
70
Finance
70
General
70
Healthcare
70
3d
70
Biology
70
Tool Calling
70
Video
70
Vision
70
Long Context
60
Physics
60
Chemistry
60
Agents
50
Economics
50
Factuality
30

Pricing

Input Price$0.2 / 1M tokens
Output Price$0.6 / 1M tokens
Blended Price (3:1)$0.3 / 1M tokens

Speed

Tokens/sec122.4
Time to First Token1.11s
Time to Answer1.11s

Provider Price Ranking

Provider Price Ranking

9 providers

Cheapest: OpenRouterMost Expensive: SiliconFlow
ProviderInputOutput
1OpenRouterCheapest
$0.13
$1.56
2Kilo Gateway
$0.13
$1.56
3NEAR AI Cloud
$0.15
$0.55
4AlibabaPRIMARY
$0.2
$0.6
5NovitaAI
$0.2
$1
6LLM Gateway
$0.2
$1
7evroc
$0.24
$0.94
8SiliconFlow (China)
$0.29
$1
9SiliconFlow
$0.29
$1

Compare pricing across different API providers for this model.

External Sources