Qwen2.5 VL 32B 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
2025-02-28
Parameters
33.5B
Context Length
—
Modalities
—
Capability Radar
60
general
90
coding
70
reasoning
43
scienceest.
40
agents
70
multimodal
Science is estimated from LLM Stats science scores or reasoning when no dedicated science benchmarks are available.
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Multimodal Ranking | 142 | 23.0 | LS |
Benchmark Scores (LLM Stats)
(LLM Stats (zeroeval))General
MMLU
78.4%SR
AndroidWorld_SR
22.0%SR
Language
MMLU-Pro
68.8%SR
Math
MATH
82.2%SR
MathVista-Mini
74.7%SR
MathVision
38.4%SR
Multimodal
Android Control Low_EM
93.3%SR
AITZ_EM
83.1%SR
VideoMME w/o sub.
70.5%SR
MMMU
70.0%SR
Android Control High_EM
69.6%SR
OSWorld
5.9%SR
Reasoning
HumanEvalOpenAI (2021)
91.5%SR
MBPP
0.84 / 100SR
GPQANYU + Cohere + Anthropic (2023)
46.0%SR
Video
CharadesSTA
54.2%SR
MMBench-Video
1.9%SR
Vision
DocVQADocVQA (2020)
94.8%SR
ScreenSpot
88.5%SR
InfoVQA
83.4%SR
VideoMME w sub.
77.9%SR
CC-OCR
77.1%SR
MMStar
69.5%SR
OCRBench-V2 (zh)
59.1%SR
OCRBench-V2 (en)
57.2%SR
MMMU-Pro
49.5%SR
LVBench
49.0%SR
ScreenSpot Pro
39.4%SR
AA Evaluation Indices
(Artificial Analysis)No AA evaluation data available
LLM Stats Category Scores
(LLM Stats (zeroeval))Code90
Structured Output80
Text-to-image80
Image To Text70
Language70
Legal70
Math70
Finance70
Healthcare70
Multimodal60
Reasoning60
Spatial Reasoning60
General60
Grounding60
Vision60
Long Context50
Physics50
Biology50
Chemistry50
Video50
Agents40
Pricing
No pricing data available
Speed
No speed data available
Provider Price Ranking
No provider data available