Перейти к основному содержанию

Qwen3 VL 235B A22B (Reasoning)

AlibabaQwenОткрытые весаApache 2.0 · Коммерческое использование

Описание

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.

Дата выхода
2025-09-23
Параметры
236.0B
Длина контекста
131K
Модальности
image, text, video

Радар способностей

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

Рейтинги

Оценки бенчмарков (LLM Stats)

(LLM Stats (zeroeval))

3d

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

Agents

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

Chemistry

SuperGPQA64.3%Сам.

Code

Design2Code0.93 / 100Сам.

Communication

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

Creativity

Creative Writing v385.7%Сам.

Embodied

EmbSpatialBench0.84 / 100Сам.
RoboSpatialHome0.74 / 100Сам.

Factuality

SimpleQA44.4%Сам.

Finance

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

General

MMLU-Redux93.7%Сам.
IFEvalGoogle Research (2023)88.2%Сам.
MMMUval80.6%Сам.
Include80.0%Сам.
LiveBench 2024112579.6%Сам.
MMStar78.7%Сам.
LiveCodeBench v670.1%Сам.
MMMU-Pro69.3%Сам.
SimpleVQA0.61 / 100Сам.

Grounding

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

Healthcare

VideoMMMU80.0%Сам.

Image To Text

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

Instruction Following

MIABench0.93 / 100Сам.

Language

CharadesSTA63.5%Сам.

Long Context

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

Math

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

Multimodal

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

Reasoning

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

Spatial Reasoning

RealWorldQA81.3%Сам.

Vision

ODinW43.2%Сам.

Индексы оценки AA

(Artificial Analysis)
Math Index(Artificial Analysis)
88.3
Intelligence Index(Artificial Analysis)
20.9
Aime 25(MAA (Mathematical Association of America))
0.9
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))
0.8
Gpqa(NYU + Cohere + Anthropic (2023))
0.8
Livecodebench(UC Berkeley + MIT + Cornell (2024))
0.6
Lcr(Artificial Analysis)
0.6
Ifbench(Google Research (2023))
0.6
Tau2(Sierra + U Toronto + Vector Institute (2025))
0.5
Scicode(UIUC + Argonne National Lab (2024))
0.4
Hle(Center for AI Safety + Scale AI (2025))
0.1
Terminalbench Hard(Stanford × Laude Institute (2026))
0.1

Оценки категорий LLM Stats

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

Цены

Цена ввода$0.7 / 1M токенов
Цена вывода$8.4 / 1M токенов
Смешанная цена (3:1)$2.625 / 1M токенов

Скорость

Токенов/сек0.0
Задержка первого токена0.00s
Время до первого ответа0.00s

Рейтинг цен провайдеров

Рейтинг цен провайдеров

7 провайдеров

Самый дешевый: Venice AIСамый дорогой: NovitaAI
ПровайдерВводВывод
1Venice AIСамый дешевый
$0.21
$1.9
2Alibaba (China)
$0.28671
$1.14682
3OpenRouter
$0.4
$4
4Kilo Gateway
$0.4
$4
5Cortecs
$0.617
$3.119
6AlibabaОсновной
$0.7
$8.4
7NovitaAI
$0.98
$3.95

Сравнение цен разных API-провайдеров для этой модели.

Внешние ссылки