QvQ-72B-Preview
Multimodal
Zero-eval
#1OlympiadBench
#3MathVision
by Alibaba
About
QvQ-72B-Preview is a multimodal language model developed by Alibaba. The model shows competitive results across 4 benchmarks. Notable strengths include MathVista (71.4%), MMMU (70.3%), MathVision (35.9%). As a multimodal model, it can process and understand text, images, and other input formats seamlessly. It's licensed for commercial use, making it suitable for enterprise applications. Released in 2024, it represents Alibaba's latest advancement in AI technology.
Timeline
AnnouncedDec 25, 2024
ReleasedDec 25, 2024
Specifications
Capabilities
Multimodal
License & Family
License
Qwen
Base ModelQwen2-VL-72B-Instruct
Benchmark Performance Overview
Performance metrics and category breakdown
Overall Performance
4 benchmarks
Average Score
49.5%
Best Score
71.4%
High Performers (80%+)
0Top Categories
vision
70.3%
math
53.6%
general
20.4%
Benchmark Performance
Top benchmark scores with normalized values (0-100%)
Ranking Across Benchmarks
Position relative to other models on each benchmark
MathVista
Rank #9 of 35
#6o1
71.8%
#7GPT-4.1
72.2%
#8GPT-4.5
72.3%
#9QvQ-72B-Preview
71.4%
#10Llama 4 Scout
70.7%
#11Pixtral Large
69.4%
#12Grok-2
69.0%
MMMU
Rank #19 of 52
#16Gemini 2.0 Flash
70.7%
#17GPT-4o
72.2%
#18GPT-4.1 mini
72.7%
#19QvQ-72B-Preview
70.3%
#20Qwen2.5 VL 72B Instruct
70.2%
#21Kimi-k1.5
70.0%
#22Qwen2.5 VL 32B Instruct
70.0%
MathVision
Rank #3 of 5
#1Qwen2.5 VL 72B Instruct
38.1%
#2Qwen2.5 VL 32B Instruct
38.4%
#3QvQ-72B-Preview
35.9%
#4Qwen2.5 VL 7B Instruct
25.1%
#5Qwen2.5-Omni-7B
25.0%
OlympiadBench
Rank #1 of 1
#1QvQ-72B-Preview
20.4%
All Benchmark Results for QvQ-72B-Preview
Complete list of benchmark scores with detailed information
MathVista MathVista benchmark | math | text | 0.71 | 71.4% | Self-reported |
MMMU MMMU benchmark | vision | multimodal | 0.70 | 70.3% | Self-reported |
MathVision MathVision benchmark | math | multimodal | 0.36 | 35.9% | Self-reported |
OlympiadBench OlympiadBench benchmark | general | text | 0.20 | 20.4% | Self-reported |