QvQ-72B-Preview

Unknown Developer

This innovative research model explores the frontiers of visual reasoning and step-by-step problem-solving. Designed for complex, multi-modal tasks in science and mathematics, it demonstrates impressive performance. However, it's still under development and has some shortcomings, including occasional language confusion and the potential to get stuck in repetitive reasoning patterns.

Model Specifications

Technical details and capabilities of QvQ-72B-Preview

Core Specifications

73.4B Parameters

Model size and complexity

32.8K / 32.8K

Input / Output tokens

December 24, 2024

Release date

Capabilities & License

Multimodal Support
Supported
Web Hydrated
No
License
qwen

Resources

API Reference
https://huggingface.co/Qwen/QVQ-72B-Preview
Code Repository
https://github.com/QwenLM/Qwen2

Performance Insights

Check out how QvQ-72B-Preview handles various AI tasks through comprehensive benchmark results.

80
60
40
20
0
71.4
MathVista
71.4
(89%)
70.3
MMMU
70.3
(88%)
35.9
MathVision
35.9
(45%)
20.4
OlympiadBench
20.4
(26%)
MathVista
MMMU
MathVision
OlympiadBench

Detailed Benchmarks

Dive deeper into QvQ-72B-Preview's performance across specific task categories. Expand each section to see detailed metrics and comparisons.

Non categorized

MathVista

Current model
Other models
Avg (70.1%)

Providers Pricing Coming Soon

We're working on gathering comprehensive pricing data from all major providers for QvQ-72B-Preview. Compare costs across platforms to find the best pricing for your use case.

OpenAI
Anthropic
Google
Mistral AI
Cohere

Share your feedback

Hi, I'm Charlie Palars, the founder of Deepranking.ai. I'm always looking for ways to improve the site and make it more useful for you. You can write me through this form or directly through X at @palarsio.

Your feedback helps us improve our service

Stay Ahead with AI Updates

Get insights on Gemini Pro 2.5, Sonnet 3.7 and more top AI models