Перейти к основному содержанию

Qwen3 VL 32B Instruct

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
70
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 рейтинг80
50.0
LS

Оценки бенчмарков (LLM Stats)

(LLM Stats (zeroeval))

Chat

MM-MT-Bench8.40 / 100Сам.
IFEvalGoogle Research (2023)84.7%Сам.
Multi-IF72.0%Сам.

Creativity

Creative Writing v385.6%Сам.

General

MMLU86.4%Сам.
MLVU-M82.1%Сам.
Include74.0%Сам.
BFCL-v370.2%Сам.
Arena-Hard v264.7%Сам.

Language

MMLU-Redux89.8%Сам.
MMLU-Pro78.6%Сам.
MMLU-ProX73.4%Сам.

Math

MathVista-Mini83.8%Сам.
LiveBench 2024112572.2%Сам.
AIME 202566.2%Сам.
MathVision63.4%Сам.
PolyMATH40.5%Сам.

Multimodal

OSWorld32.6%Сам.

Reasoning

CharXiv-D90.5%Сам.
GPQANYU + Cohere + Anthropic (2023)68.9%Сам.
CharXiv-R62.8%Сам.
SuperGPQA54.6%Сам.
LiveCodeBench v643.8%Сам.

Video

CharadesSTA61.2%Сам.

Vision

DocVQAtest96.9%Сам.
ScreenSpot95.8%Сам.
OCRBench89.5%Сам.
AI2D89.5%Сам.
InfoVQAtest87.0%Сам.
CC-OCR80.3%Сам.
RealWorldQA79.0%Сам.
MMStar77.7%Сам.
MMMU (val)76.0%Сам.
MVBench72.8%Сам.
MuirBench72.8%Сам.
OCRBench-V2 (en)67.4%Сам.
BLINK67.3%Сам.
MMMU-Pro65.3%Сам.
LVBench63.8%Сам.
Hallusion Bench63.8%Сам.
OCRBench-V2 (zh)59.2%Сам.
ScreenSpot Pro57.9%Сам.
ERQA48.8%Сам.
ODinW46.6%Сам.

Writing

WritingBench82.9%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
Structured Output
80
Grounding
80
Creativity
80
Text-to-image
80
Writing
80
Image To Text
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

Цены

Нет данных о ценах

Скорость

Нет данных о скорости

Рейтинг цен провайдеров

Нет данных провайдеров

Внешние ссылки