Skip to main content
AITier

Qwen2.5 VL 7B Instruct

Alibaba Cloud / Qwen TeamQwenOpen WeightApache 2.0 · Commercial OK

Description

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.

Release Date
2025-01-26
Parameters
8.3B
Context Length
—
Modalities
—

Capability Radar

50
general
0
coding
50
reasoning
51
scienceest.
50
agents
90
multimodal

Science uses a reasoning proxy when dedicated science benchmarks are unavailable.

Rankings

Domain#RankScoreSource
Agents & Tools35
62.0
LS
Multimodal Ranking59
71.0
LS
Reasoning82
53.0
LS

Benchmark Scores (LLM Stats)

Agents

MobileMiniWob++_SR91.4%SR
AITZ_EM81.9%SR
AndroidWorld_SR25.5%SR

General

MMVet67.1%SR
MMStar63.9%SR
MMT-Bench63.6%SR
MMMU58.6%SR
MMMU-Pro38.3%SR

Grounding

ScreenSpot84.7%SR
ScreenSpot Pro29.0%SR

Image To Text

DocVQA95.7%SR
OCRBench86.4%SR
TextVQA84.9%SR

Language

CharadesSTA43.6%SR

Long Context

MLVU70.2%SR
LongVideoBench54.7%SR
LVBench45.3%SR

Math

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

Multimodal

Android Control Low_EM91.4%SR
ChartQA87.3%SR
MMBench84.3%SR
InfoVQA82.6%SR
CC-OCR77.8%SR
TempCompass71.7%SR
VideoMME w sub.71.6%SR
PerceptionTest70.5%SR
MVBench69.6%SR
VideoMME w/o sub.65.1%SR
Android Control High_EM60.1%SR
MMBench-Video1.8%SR

Reasoning

Hallusion Bench52.9%SR

AA Evaluation Indices

No AA evaluation data available

LLM Stats Category Scores

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

Pricing

No pricing data available

Speed

No speed data available

Available Providers

(LS internal units)

No provider data available

External Sources

LLM Stats