Skip to main content

Qwen3 VL 235B A22B 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
2025-09-23
Parameters
236.0B
Context Length
262K
Modalities
image, text, video

Capability Radar

90
general
0
coding
80
reasoning
51
scienceest.
70
agents
90
multimodal

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

Rankings

Domain#RankScoreSource
Multimodal Ranking67
54.0
LS

Benchmark Scores (LLM Stats)

(LLM Stats (zeroeval))

Chat

MM-MT-Bench8.50 / 100SR
IFEvalGoogle Research (2023)87.8%SR
Multi-IF76.3%SR

Creativity

Creative Writing v386.5%SR

Factuality

SimpleQA51.9%SR

General

MMLU88.8%SR
MultiPL-E86.1%SR
CSimpleQA83.4%SR
Include80.0%SR
Arena-Hard v277.4%SR
BFCL-v367.7%SR
AndroidWorld_SR63.7%SR

Language

MMLU-Redux92.2%SR
MMLU-Pro81.8%SR
MMLU-ProX77.8%SR

Math

MathVista-Mini84.9%SR
LiveBench 2024112574.8%SR
AIME 202574.7%SR
MathVision66.5%SR
HMMT2557.4%SR

Multimodal

VideoMME w/o sub.79.2%SR
VideoMMMU74.7%SR
OSWorld66.7%SR

Reasoning

CharXiv-R62.1%SR
LiveCodeBench v561.4%SR
SuperGPQA60.4%SR
LiveCodeBench v654.3%SR

Video

MLVU84.3%SR
CharadesSTA64.8%SR

Vision

DocVQAtest97.1%SR
ScreenSpot95.4%SR
OCRBench92.0%SR
MMBench-V1.189.9%SR
AI2D89.7%SR
InfoVQAtest89.2%SR
CC-OCR82.2%SR
RealWorldQA79.3%SR
MMMUval78.7%SR
MMStar78.4%SR
MuirBench72.8%SR
BLINK70.7%SR
MMMU-Pro68.1%SR
LVBench67.7%SR
OCRBench-V2 (en)67.1%SR
Hallusion Bench63.2%SR
ScreenSpot Pro62.0%SR
OCRBench-V2 (zh)61.8%SR
ERQA51.3%SR
ODinW48.6%SR

Writing

WritingBench85.5%SR

AA Evaluation Indices

(Artificial Analysis)

No AA evaluation data available

LLM Stats Category Scores

(LLM Stats (zeroeval))
Chat
3
Communication
3
Multimodal
1
General
90
Instruction Following
80
Language
80
Legal
80
Long Context
80
Math
80
Structured Output
80
Finance
80
Grounding
80
Healthcare
80
Creativity
80
Text-to-image
80
Video
80
Writing
80
Image To Text
70
Reasoning
70
Spatial Reasoning
70
3d
70
Agents
70
Tool Calling
70
Vision
70
Physics
60
Chemistry
60
Economics
60
Factuality
50

Pricing

Input Price$0.215 / 1M tokens
Output Price$1.39 / 1M tokens
Blended Price (3:1)$0.37 / 1M tokens
Cache Read Price$0.1 / 1M tokens

Speed

Tokens/sec43.3
Time to First Token1.22s
Time to Answer1.22s

Provider Price Ranking

Provider Price Ranking

10 providers

Cheapest: DeepInfraMost Expensive: OrcaRouter
ProviderInputOutput
1DeepInfraCheapest
$0.2
$0.88
2DevPass (LLM Gateway)
$0.2
$0.88
3OpenRouter
$0.21
$1.9
4Kilo Gateway
$0.21
$1.9
5Merge Gateway
$0.21
$1.9
6AlibabaPRIMARY
$0.215
$1.39
7NanoGPT
$0.3
$1.9
8Helicone
$0.3
$1.5
9Prime Inference
$0.3
$1.5
10OrcaRouter
$0.4
$1.6

Compare pricing across different API providers for this model.

External Sources