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
262K
Modalities
image, text, video

Capability Radar

80
general
0
coding
70
reasoning
60
scienceest.
70
agents
100
multimodal

Science is estimated from LLM Stats science scores or reasoning when no dedicated science benchmarks are available.

Rankings

Domain#RankScoreSource
Multimodal Ranking110
38.0
LS

Benchmark Scores (LLM Stats)

(LLM Stats (zeroeval))

Chat

MM-MT-Bench8.10 / 100SR
IFEvalGoogle Research (2023)85.8%SR
Multi-IF66.1%SR

Creativity

Creative Writing v384.6%SR

Factuality

SimpleQA27.0%SR

General

MMLU85.0%SR
MLVU-M81.3%SR
Include71.6%SR
BFCL-v366.3%SR
Arena-Hard v258.5%SR

Language

MMLU-Redux88.4%SR
MMLU-Pro77.8%SR
MMLU-ProX70.9%SR

Math

MathVista-Mini80.1%SR
AIME 202569.3%SR
LiveBench 2024112565.4%SR
MathVision60.2%SR
HMMT2550.6%SR
PolyMATH44.3%SR

Multimodal

Video-MME74.5%SR
VideoMMMU68.7%SR
OSWorld30.3%SR

Reasoning

CharXiv-D85.5%SR
GPQANYU + Cohere + Anthropic (2023)70.4%SR
SuperGPQA53.1%SR
CharXiv-R48.9%SR
LiveCodeBench v642.6%SR

Video

CharadesSTA63.5%SR

Vision

DocVQAtest95.0%SR
ScreenSpot94.7%SR
OCRBench90.3%SR
MMBench-V1.187.0%SR
AI2D85.0%SR
InfoVQAtest82.0%SR
CC-OCR80.7%SR
MMMU (val)74.2%SR
RealWorldQA73.7%SR
MVBench72.3%SR
MMStar72.1%SR
BLINK67.7%SR
OCRBench-V2 (en)63.2%SR
MuirBench62.9%SR
LVBench62.5%SR
Hallusion Bench61.5%SR
ScreenSpot Pro60.5%SR
MMMU-Pro60.4%SR
OCRBench-V2 (zh)57.8%SR
ODinW47.5%SR
ERQA43.0%SR

Writing

WritingBench82.6%SR

AA Evaluation Indices

(Artificial Analysis)

No AA evaluation data available

LLM Stats Category Scores

(LLM Stats (zeroeval))
Chat
3
Communication
3
Multimodal
100
Instruction Following
80
Language
80
Structured Output
80
General
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
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$0.35 / 1M tokens
Output Price$0.6 / 1M tokens
Blended Price (3:1)$0.2625 / 1M tokens

Speed

Tokens/sec43.9
Time to First Token2.38s
Time to Answer2.38s

Provider Price Ranking

Provider Price Ranking

9 providers

Cheapest: DeepInfraMost Expensive: Alibaba
ProviderInputOutput
1DeepInfraCheapest
$0.15
$0.6
2OpenRouter
$0.15
$0.6
3Kilo Gateway
$0.15
$0.6
4DevPass (LLM Gateway)
$0.15
$0.6
5Merge Gateway
$0.15
$0.6
6Novita AI
$0.2
$0.7
7Prime Inference
$0.2
$0.7
8Phala
$0.2
$0.7
9AlibabaPRIMARY
$0.35
$0.6

Compare pricing across different API providers for this model.

External Sources