Перейти к основному содержанию

Qwen3 VL 32B (Reasoning)

AlibabaQwenОткрытые весаApache 2.0 · Коммерческое использование

Описание

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.

Дата выхода
2025-10-21
Параметры
33.0B
Длина контекста
—
Модальности
—

Радар способностей

90
general
0
coding
80
reasoning
60
scienceоцен.
70
agents
90
multimodal

При отсутствии специализированных научных бенчмарков Science оценивается по научным категориям LLM Stats или на основе рассуждений.

Рейтинги

Домен#МестоОценкаИсточник
Мультимодальный рейтинг60
55.0
LS

Оценки бенчмарков (LLM Stats)

(LLM Stats (zeroeval))

Chat

MM-MT-Bench8.30 / 100Сам.
IFEvalGoogle Research (2023)87.8%Сам.
Multi-IF78.0%Сам.

Creativity

Creative Writing v383.3%Сам.

Factuality

SimpleQA55.4%Сам.

General

MMLU88.7%Сам.
Include76.3%Сам.
BFCL-v371.7%Сам.
AndroidWorld_SR63.7%Сам.
Arena-Hard v260.5%Сам.

Language

MMLU-Redux91.9%Сам.
MMLU-Pro82.1%Сам.
MMLU-ProX77.2%Сам.

Math

MathVista-Mini85.9%Сам.
AIME 202583.7%Сам.
LiveBench 2024112574.7%Сам.
MathVision70.2%Сам.
PolyMATH52.0%Сам.

Multimodal

VideoMMMU79.0%Сам.
VideoMME w/o sub.77.3%Сам.
OSWorld41.0%Сам.

Reasoning

CharXiv-D90.2%Сам.
GPQANYU + Cohere + Anthropic (2023)73.1%Сам.
LiveCodeBench v665.6%Сам.
CharXiv-R65.2%Сам.
SuperGPQA59.0%Сам.

Video

CharadesSTA62.8%Сам.

Vision

DocVQAtest96.1%Сам.
ScreenSpot95.7%Сам.
MMBench-V1.190.8%Сам.
InfoVQAtest89.2%Сам.
AI2D88.9%Сам.
OCRBench85.5%Сам.
MuirBench80.3%Сам.
MMStar79.4%Сам.
RealWorldQA78.4%Сам.
MMMU (val)78.1%Сам.
MVBench73.2%Сам.
BLINK68.5%Сам.
OCRBench-V2 (en)68.4%Сам.
MMMU-Pro68.1%Сам.
Hallusion Bench67.4%Сам.
LVBench62.6%Сам.
OCRBench-V2 (zh)62.1%Сам.
ScreenSpot Pro57.1%Сам.
ERQA52.3%Сам.

Writing

WritingBench86.2%Сам.

Индексы оценки AA

(Artificial Analysis)

Нет данных AA оценки

Оценки категорий LLM Stats

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

Цены

Нет данных о ценах

Скорость

Нет данных о скорости

Рейтинг цен провайдеров

Нет данных провайдеров

Внешние ссылки