Model Comparison

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

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.

Qwen2.5 32B Instruct

Alibaba

Qwen2.5 32B Instruct is a language model developed by Alibaba. It achieves strong performance with an average score of 74.3% across 18 benchmarks. It excels particularly in GSM8k (95.9%), HumanEval (88.4%), HellaSwag (85.2%). The model shows particular specialization in math tasks with an average performance of 89.5%. It's licensed for commercial use, making it suitable for enterprise applications. Released in 2024, it represents Alibaba's latest advancement in AI technology.

Qwen2.5 14B Instruct

Alibaba

2024-09-19

Qwen2.5 32B Instruct

Alibaba

2024-09-19

0 days newer

Average performance across 16 common benchmarks

Qwen2.5 14B Instruct

Average Score:70.0%

Qwen2.5 32B Instruct

+3.1%

Average Score:73.1%

Performance comparison across key benchmark categories

Qwen2.5 14B Instruct

math

87.4%

reasoning

67.3%

code

70.0%

general

67.4%

factuality

+0.6%

58.4%

Qwen2.5 32B Instruct

math

+2.1%

89.5%

reasoning

+11.9%

79.2%

code

+3.0%

73.0%

general

+3.9%

71.3%

factuality

57.8%

Benchmark Scores - Detailed View

Side-by-side comparison of all benchmark scores

Provider Availability & Performance

Available providers and their performance metrics

Qwen2.5 14B Instruct

0 providers

Qwen2.5 32B Instruct

0 providers

Qwen2.5 14B Instruct

Avg Score:70.0%

Providers:0

Qwen2.5 32B Instruct

+3.1%

Avg Score:73.1%

Providers:0