跳轉到主要內容

Qwen3 VL 30B A3B (Reasoning)

AlibabaQwen開源權重Apache 2.0 · 商用許可

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.

發布日期
2025-10-03
參數規模
31.0B
上下文長度
131K
支援模態
image, text, video

能力雷達圖

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

排行榜排名

領域#排名分數來源
智慧體能力模型榜98
40.0
LS
程式碼能力榜266
45.0
AA
通用能力榜332
39.0
AA
多模態榜63
41.0
LS
科學能力306
45.0
AA

基準測試分數 (LLM Stats)

(LLM Stats (zeroeval))

3d

BLINK65.4%自報

Agents

BFCL-v368.6%自報
OSWorld30.6%自報

Biology

GPQANYU + Cohere + Anthropic (2023)74.4%自報

Chemistry

SuperGPQA56.4%自報

Communication

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

Creativity

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

Factuality

SimpleQA23.9%自報

Finance

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

General

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

Grounding

ScreenSpot94.7%自報
ScreenSpot Pro57.3%自報

Healthcare

VideoMMMU75.0%自報

Image To Text

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

Language

CharadesSTA62.7%自報

Long Context

LVBench59.2%自報

Math

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

Multimodal

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

Reasoning

Hallusion Bench66.0%自報
ERQA45.3%自報

Spatial Reasoning

RealWorldQA77.4%自報

Vision

ODinW42.3%自報

AA 評測指數

(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 分類評分

(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

定價

輸入價格$0.2 / 1M tokens
輸出價格$2.4 / 1M tokens
混合價格(3:1)$0.75 / 1M tokens

速度

Tokens/秒0.0
首Token延遲0.00s
首回答延遲0.00s

供應商價格排行

供應商價格排行

5 個供應商

最便宜: Alibaba (China)最貴: Kilo Gateway
供應商輸入輸出
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

比較該模型在不同 API 供應商之間的定價。

外部連結