Skip to main content
AITier

Qwen2-VL-72B-Instruct

Alibaba Cloud / Qwen TeamQwenOpen Weighttongyi-qianwen

Description

An instruction-tuned, large multimodal model that excels at visual understanding and step-by-step reasoning. It supports image and video input, with dynamic resolution handling and improved positional embeddings (M-ROPE), enabling advanced capabilities such as complex problem solving, multilingual text recognition in images, and agent-like interactions in video contexts.

Release Date
2024-08-29
Parameters
73.4B
Context Length
—
Modalities
—

Capability Radar

60
general
0
coding
70
reasoning
51
scienceest.
0
agents
90
multimodal

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

Rankings

Domain#RankScoreSource
Multimodal Ranking36
78.0
LS
Reasoning6
92.0
LS

Benchmark Scores (LLM Stats)

General

MMVetGPT4Turbo74.0%SR
MMMUval64.5%SR
MMMU-Pro46.2%SR

Image To Text

OCRBench87.7%SR
TextVQA85.5%SR

Long Context

EgoSchema77.9%SR

Math

MathVista-Mini70.5%SR

Multimodal

DocVQAtest96.5%SR
ChartQA88.3%SR
MMBench86.5%SR
InfoVQAtest84.5%SR
MVBench73.6%SR
MTVQA30.9%SR

Reasoning

VCR_en_easy91.9%SR

Spatial Reasoning

RealWorldQA77.8%SR

AA Evaluation Indices

No AA evaluation data available

LLM Stats Category Scores

Image To Text
90
Spatial Reasoning
80
Vision
80
Long Context
80
Multimodal
80
Video
70
Math
70
Reasoning
70
General
60
Healthcare
60

Pricing

No pricing data available

Speed

No speed data available

Available Providers

(LS internal units)

No provider data available

External Sources

LLM Stats