跳转到主要内容

Qwen2.5 VL 7B Instruct

Alibaba Cloud / Qwen TeamQwen开源权重Apache 2.0 · 商用许可

描述

Qwen2.5-VL is a vision-language model from the Qwen family. Key enhancements include visual understanding (objects, text, charts, layouts), visual agent capabilities (tool use, computer/phone control), long video comprehension with event pinpointing, visual localization (bounding boxes/points), and structured output generation.

发布日期
2025-01-26
参数规模
8.3B
上下文长度
—
支持模态
—

能力雷达图

60
general
0
coding
50
reasoning
51
science估算
50
agents
90
multimodal

缺少专门科学评测时,Science 由 LLM Stats 科学得分或推理能力估算。

排行榜排名

领域#排名分数来源
多模态榜141
18.0
LS

基准测试分数 (LLM Stats)

(LLM Stats (zeroeval))

General

AndroidWorld_SR25.5%自报

Math

MathVista-Mini68.2%自报
MathVision25.1%自报

Multimodal

MobileMiniWob++_SR91.4%自报
Android Control Low_EM91.4%自报
AITZ_EM81.9%自报
VideoMME w/o sub.65.1%自报
Android Control High_EM60.1%自报
MMMU58.6%自报

Reasoning

ChartQAMasry et al. (2022)87.3%自报

Video

PerceptionTest70.5%自报
MLVU70.2%自报
CharadesSTA43.6%自报
MMBench-Video1.8%自报

Vision

DocVQADocVQA (2020)95.7%自报
OCRBench86.4%自报
TextVQA84.9%自报
ScreenSpot84.7%自报
MMBench84.3%自报
InfoVQA82.6%自报
CC-OCR77.8%自报
TempCompass71.7%自报
VideoMME w sub.71.6%自报
MVBench69.6%自报
MMVet67.1%自报
MMStar63.9%自报
MMT-Bench63.6%自报
LongVideoBench54.7%自报
Hallusion Bench52.9%自报
LVBench45.3%自报
MMMU-Pro38.3%自报
ScreenSpot Pro29.0%自报

AA 评测指数

(Artificial Analysis)

暂无 AA 评测数据

LLM Stats 分类评分

(LLM Stats (zeroeval))
Image To Text
90
Structured Output
80
Text-to-image
80
Long Context
60
Multimodal
60
Reasoning
60
Spatial Reasoning
60
General
60
Grounding
60
Healthcare
60
Vision
60
Math
50
Agents
50
Video
50
Language
40

定价

暂无定价数据

速度

暂无速度数据

供应商价格排行

暂无提供商数据

外部链接