Model Comparison

Comprehensive side-by-side analysis of model capabilities and performance

Qwen2 72B Instruct

Alibaba

Qwen2 72B Instruct is a language model developed by Alibaba. It achieves strong performance with an average score of 73.6% across 17 benchmarks. It excels particularly in GSM8k (91.1%), CMMLU (90.1%), HellaSwag (87.6%). The model shows particular specialization in code tasks with an average performance of 82.3%. Released in 2024, it represents Alibaba's latest advancement in AI technology.

Qwen2.5 14B Instruct

Alibaba

Qwen2.5 14B Instruct is a language model developed by Alibaba. It achieves strong performance with an average score of 70.0% across 16 benchmarks. It excels particularly in GSM8k (94.8%), HumanEval (83.5%), MBPP (82.0%). The model shows particular specialization in math tasks with an average performance of 87.4%. It's licensed for commercial use, making it suitable for enterprise applications. Released in 2024, it represents Alibaba's latest advancement in AI technology.

Qwen2 72B Instruct

Alibaba

2024-07-23

Qwen2.5 14B Instruct

Alibaba

2024-09-19

1 month newer

Average performance across 12 common benchmarks

Qwen2 72B Instruct

Average Score:68.8%

Qwen2.5 14B Instruct

+1.9%

Average Score:70.7%

Performance comparison across key benchmark categories

Qwen2 72B Instruct

math

75.4%

code

+12.3%

82.3%

reasoning

+13.2%

80.5%

general

+0.5%

67.9%

factuality

54.8%

Qwen2.5 14B Instruct

math

+12.0%

87.4%

code

70.0%

reasoning

67.3%

general

67.4%

factuality

+3.6%

58.4%

Benchmark Scores - Detailed View

Side-by-side comparison of all benchmark scores

Provider Availability & Performance

Available providers and their performance metrics

Qwen2 72B Instruct

0 providers

Qwen2.5 14B Instruct

0 providers

Qwen2 72B Instruct

Avg Score:68.8%

Providers:0

Qwen2.5 14B Instruct

+1.9%

Avg Score:70.7%

Providers:0