Back to all models
Q

Qwen 2.5 72B

AlibabaReleased 2024-09-19
Official Page

Alibaba's powerful open-source model with strong multilingual performance, particularly for Chinese and other Asian languages.

Overall Score
74%
Cost Efficiency
100
Context Window
128K

Strengths

  • ✓Strong multilingual support
  • ✓Open-source
  • ✓Good for Asian languages
  • ✓Competitive performance

Weaknesses

  • ✗Weaker in English benchmarks
  • ✗Limited ecosystem outside China
Architecture
Transformer
Parameters
72B
Input
$0/M
Output
$0/M

Benchmark Performance

BenchmarkDescriptionScoreCategoryBar
MMLUMassive Multitask Language Understanding84%knowledge
HumanEvalCode generation accuracy85.2%coding
MATHMathematical reasoning83.4%math
GSM8KGrade school math86.1%math
GPQAGraduate-level science Q&A44.5%reasoning
HellaSwagCommon sense reasoning84.2%reasoning
SWE-benchSoftware engineering problems31.2%coding
ARC-CAI2 Reasoning Challenge92%reasoning
AI
ModelBench

The open benchmark platform for comparing the latest AI models and their capabilities.

Platform

  • Compare Models
  • All Models
  • Methodology

AI Labs

  • OpenAI
  • Anthropic
  • Google DeepMind
  • Meta AI

Resources

  • Documentation
  • Benchmark Guide
  • API Reference
Benchmarks are sourced from official model cards and independent evaluations. Data is for informational purposes only.
© 2026 ModelBench. Built for the AI community.