Перейти к основному содержанию

Qwen3 VL 4B 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
2025-10-14
Параметры
4.0B
Длина контекста
—
Модальности
image, text

Радар способностей

23
general
29
coding
37
reasoning
27
science
60
agents
90
multimodal

Рейтинги

Домен#МестоОценкаИсточник
Рейтинг кодинга543
16.0
AA
Общий рейтинг530
26.0
AA
Мультимодальный рейтинг139
26.0
LS
Наука587
18.0
AA

Оценки бенчмарков (LLM Stats)

(LLM Stats (zeroeval))

Chat

MM-MT-Bench7.50 / 100Сам.
IFEvalGoogle Research (2023)82.3%Сам.

Factuality

SimpleQA48.0%Сам.

General

MMLU77.2%Сам.
MLVU-M75.3%Сам.
BFCL-v363.3%Сам.
Include61.4%Сам.

Language

MMLU-Redux81.5%Сам.
MMLU-Pro67.1%Сам.
MMLU-ProX59.4%Сам.

Math

MathVista-Mini73.7%Сам.
LiveBench 2024112560.9%Сам.
MathVision51.6%Сам.
AIME 202546.6%Сам.
HMMT2530.7%Сам.
PolyMATH28.8%Сам.

Multimodal

VideoMMMU56.2%Сам.
OSWorld26.2%Сам.

Reasoning

CharXiv-D76.2%Сам.
SuperGPQA40.3%Сам.
CharXiv-R39.7%Сам.
LiveCodeBench v637.9%Сам.

Video

CharadesSTA55.5%Сам.

Vision

DocVQAtest95.3%Сам.
ScreenSpot94.0%Сам.
OCRBench88.1%Сам.
MMBench-V1.185.1%Сам.
AI2D84.1%Сам.
InfoVQAtest80.3%Сам.
CC-OCR76.2%Сам.
RealWorldQA70.9%Сам.
MMStar69.8%Сам.
MVBench68.9%Сам.
MMMU (val)67.4%Сам.
BLINK65.8%Сам.
MuirBench63.8%Сам.
OCRBench-V2 (en)63.7%Сам.
ScreenSpot Pro59.5%Сам.
OCRBench-V2 (zh)57.6%Сам.
Hallusion Bench57.6%Сам.
LVBench56.2%Сам.
MMMU-Pro53.2%Сам.
ODinW48.2%Сам.
ERQA41.3%Сам.

Writing

WritingBench82.5%Сам.

Индексы оценки AA

(Artificial Analysis)
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))
63.4
Gpqa(NYU + Cohere + Anthropic (2023))
37.1
Math Index(Artificial Analysis)
37.0
Aime 25(MAA (Mathematical Association of America))
37.0
Ifbench(Google Research (2023))
31.8
Livecodebench(UC Berkeley + MIT + Cornell (2024))
29.0
Tau2(Sierra + U Toronto + Vector Institute (2025))
23.4
Lcr(Artificial Analysis)
14.0
Intelligence Index(Artificial Analysis)
5.7
Hle(Center for AI Safety + Scale AI (2025))
3.6
Terminalbench Hard(Stanford × Laude Institute (2026))
0.0

Оценки категорий LLM Stats

(LLM Stats (zeroeval))
Chat
4
Communication
4
Multimodal
90
Instruction Following
80
General
80
Grounding
80
Creativity
80
Text-to-image
80
Writing
80
Image To Text
70
Language
70
Legal
70
Structured Output
70
3d
70
Long Context
60
Math
60
Reasoning
60
Spatial Reasoning
60
Finance
60
Healthcare
60
Tool Calling
60
Video
60
Vision
60
Factuality
50
Physics
40
Agents
40
Chemistry
40
Economics
40

Цены

Цена вводаБесплатно
Цена выводаБесплатно
Смешанная цена (3:1)Бесплатно

Скорость

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

Рейтинг цен провайдеров

Нет данных провайдеров

Внешние ссылки