मुख्य सामग्री पर जाएं

Qwen3 VL 235B A22B (Reasoning)

AlibabaQwenओपन वेटApache 2.0 · व्यावसायिक उपयोग

विवरण

Qwen3-VL-235B-A22B-Thinking is the most powerful vision-language model in the Qwen series, featuring 236B parameters with MoE architecture for reasoning-enhanced multimodal understanding. Key capabilities include: Visual Agent (operates PC/mobile GUIs, recognizes elements, invokes tools), Visual Coding (generates Draw.io/HTML/CSS/JS from images/videos), Advanced Spatial Perception (2D grounding and 3D grounding for spatial reasoning and embodied AI), Long Context & Video Understanding (native 256K context expandable to 1M, handles hours-long video with second-level indexing), Enhanced Multimodal Reasoning (excels in STEM/Math with causal analysis), Upgraded Visual Recognition (celebrities, anime, products, landmarks, flora/fauna), and Expanded OCR (32 languages, robust in low light/blur/tilt). Architecture innovations include Interleaved-MRoPE for positional embeddings, DeepStack for multi-level ViT feature fusion, and Text-Timestamp Alignment for precise video temporal modeling.

रिलीज़ तिथि
2025-09-23
पैरामीटर
236.0B
संदर्भ लंबाई
131K
मोडैलिटीज़
image, text, video

क्षमता रडार

38
general
59
coding
86
reasoning
51
scienceअनुमानित
70
agents
100
multimodal

समर्पित विज्ञान बेंचमार्क उपलब्ध न होने पर Science तर्क प्रॉक्सी का उपयोग करके अनुमान लगाता है।

रैंकिंग

बेंचमार्क स्कोर (LLM Stats)

3d

Objectron0.71 / 100स्वयं
BLINK67.1%स्वयं
ARKitScenes0.54 / 100स्वयं
SUNRGBD0.35 / 100स्वयं
Hypersim0.11 / 100स्वयं

Agents

SIFO0.77 / 100स्वयं
BFCL-v371.9%स्वयं
SIFO-Multiturn0.71 / 100स्वयं
OSWorld-G0.68 / 100स्वयं
OSWorld38.1%स्वयं

Chemistry

SuperGPQA64.3%स्वयं

Code

Design2Code0.93 / 100स्वयं

Communication

MM-MT-Bench8.50 / 100स्वयं
WritingBench86.7%स्वयं
Multi-IF79.1%स्वयं

Creativity

Creative Writing v385.7%स्वयं

Embodied

EmbSpatialBench0.84 / 100स्वयं
RoboSpatialHome0.74 / 100स्वयं

Factuality

SimpleQA44.4%स्वयं

Finance

MMLU90.6%स्वयं
MMLU-Pro83.8%स्वयं
MMLU-ProX80.6%स्वयं

General

MMLU-Redux93.7%स्वयं
IFEval88.2%स्वयं
MMMUval80.6%स्वयं
Include80.0%स्वयं
LiveBench 2024112579.6%स्वयं
MMStar78.7%स्वयं
LiveCodeBench v670.1%स्वयं
MMMU-Pro69.3%स्वयं
SimpleVQA0.61 / 100स्वयं

Grounding

ScreenSpot95.4%स्वयं
RefCOCO-avg0.92 / 100स्वयं
RefSpatialBench0.70 / 100स्वयं
ScreenSpot Pro61.8%स्वयं

Healthcare

VideoMMMU80.0%स्वयं

Image To Text

OCRBench87.5%स्वयं
OCRBench-V2 (en)66.8%स्वयं
OCRBench-V2 (zh)63.5%स्वयं

Instruction Following

MIABench0.93 / 100स्वयं

Language

CharadesSTA63.5%स्वयं

Long Context

MLVU83.8%स्वयं
LVBench63.6%स्वयं
MMLongBench-Doc0.56 / 100स्वयं

Math

AIME 202589.7%स्वयं
MathVista-Mini85.8%स्वयं
MathVerse-Mini0.85 / 100स्वयं
HMMT2577.4%स्वयं
MathVision74.6%स्वयं
Humanity's Last Exam13.6%स्वयं

Multimodal

DocVQAtest96.5%स्वयं
MMBench-V1.190.6%स्वयं
InfoVQAtest89.5%स्वयं
AI2D89.2%स्वयं
CC-OCR81.5%स्वयं
MuirBench80.1%स्वयं
VideoMME w/o sub.79.0%स्वयं
CharXiv-R66.1%स्वयं
VisuLogic0.34 / 100स्वयं
ZEROBench-Sub0.28 / 100स्वयं
ZEROBench0.04 / 100स्वयं

Reasoning

ZebraLogic97.3%स्वयं
CountBench0.94 / 100स्वयं
Hallusion Bench66.7%स्वयं
ERQA52.5%स्वयं

Spatial Reasoning

RealWorldQA81.3%स्वयं

Vision

ODinW43.2%स्वयं

AA मूल्यांकन सूचकांक

Math Index
88.3
Intelligence Index
20.6
Aime 25
0.9
Mmlu Pro
0.8
Gpqa
0.8
Livecodebench
0.6
Lcr
0.6
Ifbench
0.6
Tau2
0.5
Scicode
0.4
Terminalbench Hard
0.1
Hle
0.1

LLM Stats श्रेणी स्कोर

Communication
3
Multimodal
100
Creativity
90
Writing
90
Instruction Following
80
Language
80
Legal
80
Math
80
Structured Output
80
Embodied
80
Finance
80
Grounding
80
Healthcare
80
Text-to-image
80
Video
80
Image To Text
70
Long Context
70
Reasoning
70
Spatial Reasoning
70
General
70
Tool Calling
70
Vision
70
Physics
60
Agents
60
Chemistry
60
Economics
60
Factuality
40
3d
40

मूल्य निर्धारण

इनपुट मूल्य$0.84 / 1M टोकन
आउटपुट मूल्य$6.175 / 1M टोकन
मिश्रित मूल्य (3:1)$2.174 / 1M टोकन

गति

टोकन/सेकंड57.2
पहले टोकन में देरी1.16s
पहले उत्तर में देरी36.11s

प्रदाता मूल्य रैंकिंग

प्रदाता मूल्य रैंकिंग

10 प्रदाता

सबसे सस्ता: Venice AIसबसे महंगा: NovitaAI
प्रदाताइनपुटआउटपुट
1Venice AIसबसे सस्ता
$0.25
$1.5
2OpenRouter
$0.26
$2.6
3Kilo Gateway
$0.26
$2.6
4Alibaba (China)
$0.28671
$1.14682
5SiliconFlow (China)
$0.45
$3.5
6SiliconFlow
$0.45
$3.5
7NanoGPT
$0.5
$6
8LLM Gateway
$0.5
$2
9Alibaba
$0.7
$2.8
10NovitaAI
$0.98
$3.95

इस मॉडल के लिए विभिन्न API प्रदाताओं के मूल्य निर्धारण की तुलना करें।

बाहरी लिंक