メインコンテンツへスキップ

Qwen3 VL 30B A3B Instruct

AlibabaQwenOpen WeightApache 2.0 · Commercial OK

説明

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.

リリース日
2025-10-03
パラメータ
31.0B
コンテキスト長
131K
モダリティ
image, text, video

能力レーダー

33
general
28
coding
72
reasoning
43
science推定
70
agents
100
multimodal

専門的な科学ベンチマークが利用できない場合、Scienceは推論プロキシを使用して推定します。

ランキング

ドメイン#順位スコアソース
Agents & Tools69
52.0
LS
Code Ranking278
28.0
AA
General Ranking318
35.0
AA
Math Reasoning110
73.0
AA
Multimodal Ranking45
75.0
LS
Reasoning85
51.0
LS
Science234
45.0
AA

ベンチマークスコア (LLM Stats)

3d

BLINK67.7%自己申告

Agents

BFCL-v366.3%自己申告
OSWorld30.3%自己申告

Biology

GPQA70.4%自己申告

Chemistry

SuperGPQA53.1%自己申告

Communication

MM-MT-Bench8.10 / 100自己申告
WritingBench82.6%自己申告
Multi-IF66.1%自己申告

Creativity

Creative Writing v384.6%自己申告
Arena-Hard v258.5%自己申告

Factuality

SimpleQA27.0%自己申告

Finance

MMLU85.0%自己申告
MMLU-Pro77.8%自己申告
MMLU-ProX70.9%自己申告

General

MMLU-Redux88.4%自己申告
IFEval85.8%自己申告
MLVU-M81.3%自己申告
MMMU (val)74.2%自己申告
MMStar72.1%自己申告
Include71.6%自己申告
LiveBench 2024112565.4%自己申告
MMMU-Pro60.4%自己申告
LiveCodeBench v642.6%自己申告

Grounding

ScreenSpot94.7%自己申告
ScreenSpot Pro60.5%自己申告

Healthcare

VideoMMMU68.7%自己申告

Image To Text

OCRBench90.3%自己申告
OCRBench-V2 (en)63.2%自己申告
OCRBench-V2 (zh)57.8%自己申告

Language

CharadesSTA63.5%自己申告

Long Context

LVBench62.5%自己申告

Math

MathVista-Mini80.1%自己申告
AIME 202569.3%自己申告
MathVision60.2%自己申告
HMMT2550.6%自己申告
PolyMATH44.3%自己申告

Multimodal

DocVQAtest95.0%自己申告
MMBench-V1.187.0%自己申告
CharXiv-D85.5%自己申告
AI2D85.0%自己申告
InfoVQAtest82.0%自己申告
CC-OCR80.7%自己申告
Video-MME74.5%自己申告
MVBench72.3%自己申告
MuirBench62.9%自己申告
CharXiv-R48.9%自己申告

Reasoning

Hallusion Bench61.5%自己申告
ERQA43.0%自己申告

Spatial Reasoning

RealWorldQA73.7%自己申告

Vision

ODinW47.5%自己申告

AA評価指数

Math Index
72.3
Intelligence Index
16.1
Coding Index
14.3
Mmlu Pro
0.8
Aime 25
0.7
Gpqa
0.7
Livecodebench
0.5
Ifbench
0.3
Scicode
0.3
Lcr
0.2
Tau2
0.2
Hle
0.1
Terminalbench Hard
0.1

LLM Statsカテゴリスコア

Communication
3
Multimodal
100
Structured Output
80
Text-to-image
80
Writing
80
Creativity
80
Grounding
80
Instruction Following
80
Language
80
Spatial Reasoning
70
Tool Calling
70
Video
70
Vision
70
3d
70
Biology
70
Finance
70
General
70
Healthcare
70
Image To Text
70
Legal
70
Math
70
Reasoning
70
Chemistry
60
Long Context
60
Physics
60
Agents
50
Economics
50
Factuality
30

価格設定

入力価格$0.2 / 1M tokens
出力価格$0.6 / 1M tokens
混合価格(3:1)$0.3 / 1M tokens

速度

トークン/秒125.3 tokens/s
初トークン遅延1.08s
初回答遅延1.08s

利用可能なプロバイダー

(LS内部単位)
プロバイダー入力価格出力価格
Novita200K700K
DeepInfra290K990K

外部リンク