跳转到主要内容

Qwen3 VL 30B A3B (Reasoning)

AlibabaQwen开源权重Apache 2.0 · 商用许可

描述

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.

发布日期
2025-10-03
参数规模
31.0B
上下文长度
131K
支持模态
image, text, video

能力雷达图

33
general
61
coding
81
reasoning
44
science
70
agents
100
multimodal

排行榜排名

领域#排名分数来源
智能体能力模型榜98
40.0
LS
代码能力榜266
45.0
AA
通用能力榜332
39.0
AA
多模态榜63
41.0
LS
科学能力306
45.0
AA

基准测试分数 (LLM Stats)

(LLM Stats (zeroeval))

3d

BLINK65.4%自报

Agents

BFCL-v368.6%自报
OSWorld30.6%自报

Biology

GPQANYU + Cohere + Anthropic (2023)74.4%自报

Chemistry

SuperGPQA56.4%自报

Communication

MM-MT-Bench7.90 / 100自报
WritingBench85.2%自报
Multi-IF73.0%自报

Creativity

Creative Writing v382.5%自报
Arena-Hard v256.7%自报

Factuality

SimpleQA23.9%自报

Finance

MMLU87.6%自报
MMLU-Pro80.5%自报
MMLU-ProX76.1%自报

General

MMLU-Redux90.9%自报
IFEvalGoogle Research (2023)81.7%自报
MLVU-M78.9%自报
MMMU (val)76.0%自报
MMStar75.5%自报
Include74.5%自报
LiveBench 2024112572.1%自报
LiveCodeBench v664.2%自报
MMMU-Pro63.0%自报

Grounding

ScreenSpot94.7%自报
ScreenSpot Pro57.3%自报

Healthcare

VideoMMMU75.0%自报

Image To Text

OCRBench83.9%自报
OCRBench-V2 (en)62.6%自报
OCRBench-V2 (zh)60.4%自报

Language

CharadesSTA62.7%自报

Long Context

LVBench59.2%自报

Math

AIME 202583.1%自报
MathVista-Mini81.9%自报
HMMT2567.6%自报
MathVision65.7%自报
PolyMATH51.7%自报

Multimodal

DocVQAtest95.0%自报
MMBench-V1.188.9%自报
CharXiv-D86.9%自报
AI2D86.9%自报
InfoVQAtest86.0%自报
CC-OCR77.8%自报
MuirBench77.6%自报
Video-MME73.3%自报
MVBench72.0%自报
CharXiv-R56.6%自报

Reasoning

Hallusion Bench66.0%自报
ERQA45.3%自报

Spatial Reasoning

RealWorldQA77.4%自报

Vision

ODinW42.3%自报

AA 评测指数

(Artificial Analysis)
Math Index(Artificial Analysis)
82.3
Intelligence Index(Artificial Analysis)
13.4
Aime 25(MAA (Mathematical Association of America))
0.8
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))
0.8
Gpqa(NYU + Cohere + Anthropic (2023))
0.7
Livecodebench(UC Berkeley + MIT + Cornell (2024))
0.7
Ifbench(Google Research (2023))
0.5
Lcr(Artificial Analysis)
0.4
Scicode(UIUC + Argonne National Lab (2024))
0.3
Tau2(Sierra + U Toronto + Vector Institute (2025))
0.2
Hle(Center for AI Safety + Scale AI (2025))
0.1
Terminalbench Hard(Stanford × Laude Institute (2026))
0.1

LLM Stats 分类评分

(LLM Stats (zeroeval))
Communication
3
Multimodal
100
General
90
Legal
80
Structured Output
80
Instruction Following
80
Language
80
Finance
80
Grounding
80
Healthcare
80
Text-to-image
80
Math
70
Physics
70
Reasoning
70
Spatial Reasoning
70
Image To Text
70
3d
70
Biology
70
Chemistry
70
Creativity
70
Tool Calling
70
Video
70
Vision
70
Writing
70
Long Context
60
Economics
60
Agents
50
Factuality
20

定价

输入价格$0.2 / 1M tokens
输出价格$2.4 / 1M tokens
混合价格(3:1)$0.75 / 1M tokens

速度

Tokens/秒0.0
首Token延迟0.00s
首回答延迟0.00s

供应商价格排行

供应商价格排行

5 个供应商

最便宜: Alibaba (China)最贵: Kilo Gateway
供应商输入输出
1Alibaba (China)最便宜
$0.108
$0.431
2Alibaba主要
$0.2
$2.4
3OpenRouter
$0.2
$2.4
4NovitaAI
$0.2
$1
5Kilo Gateway
$0.2
$2.4

比较该模型在不同 API 供应商之间的定价。

外部链接