跳轉到主要內容

Qwen3 VL 8B (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
2025-10-14
參數規模
9.0B
上下文長度
262K
支援模態
image, text

能力雷達圖

80
general
0
coding
70
reasoning
60
science估算
60
agents
100
multimodal

缺少專門科學評測時,Science 由 LLM Stats 科學得分或推理能力估算。

排行榜排名

領域#排名分數來源
多模態榜127
34.0
LS

基準測試分數 (LLM Stats)

(LLM Stats (zeroeval))

Chat

MM-MT-Bench8.00 / 100自報
IFEvalGoogle Research (2023)83.2%自報
Multi-IF75.1%自報

Creativity

Creative Writing v382.4%自報

Factuality

SimpleQA49.6%自報

General

MMLU85.2%自報
MLVU-M75.1%自報
Include69.5%自報
BFCL-v363.0%自報
Arena-Hard v251.1%自報

Language

MMLU-Redux88.8%自報
MMLU-Pro77.3%自報
MMLU-ProX70.7%自報

Math

MathVista-Mini81.4%自報
AIME 202580.3%自報
LiveBench 2024112569.8%自報
MathVision62.7%自報
HMMT2560.6%自報
PolyMATH47.5%自報

Multimodal

VideoMMMU72.8%自報
Video-MME71.8%自報
OSWorld33.9%自報

Reasoning

CharXiv-D85.9%自報
GPQANYU + Cohere + Anthropic (2023)69.9%自報
LiveCodeBench v658.6%自報
CharXiv-R53.0%自報
SuperGPQA51.2%自報

Video

CharadesSTA59.9%自報

Vision

DocVQAtest95.3%自報
ScreenSpot93.6%自報
MMBench-V1.187.5%自報
InfoVQAtest86.0%自報
AI2D84.9%自報
OCRBench81.9%自報
MuirBench76.8%自報
CC-OCR76.3%自報
MMStar75.3%自報
MMMU (val)74.1%自報
RealWorldQA73.5%自報
MVBench69.0%自報
BLINK68.7%自報
Hallusion Bench65.4%自報
OCRBench-V2 (en)63.9%自報
MMMU-Pro60.4%自報
OCRBench-V2 (zh)59.2%自報
LVBench55.8%自報
ERQA46.8%自報
ScreenSpot Pro46.6%自報
ODinW39.8%自報

Writing

WritingBench85.5%自報

AA 評測指數

(Artificial Analysis)

暫無 AA 評測資料

LLM Stats 分類評分

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

定價

輸入價格$0.25 / 1M tokens
輸出價格$0.75 / 1M tokens
混合價格(3:1)$0.375 / 1M tokens
快取讀取價格$0.12 / 1M tokens

速度

暫無速度資料

供應商價格排行

供應商價格排行

3 個供應商

最便宜: Alibaba最貴: Kilo Gateway
供應商輸入輸出
1Alibaba主要
$0.25
$0.75
2OpenRouter
$0.25
$0.75
3Kilo Gateway
$0.25
$0.75

比較該模型在不同 API 供應商之間的定價。

外部連結