Model Comparison

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

DeepSeek R1 Distill Qwen 14B

DeepSeek

DeepSeek R1 Distill Qwen 14B is a language model developed by DeepSeek. It achieves strong performance with an average score of 71.5% across 4 benchmarks. It excels particularly in MATH-500 (93.9%), AIME 2024 (80.0%), GPQA (59.1%). It's licensed for commercial use, making it suitable for enterprise applications. Released in 2025, it represents DeepSeek's latest advancement in AI technology.

DeepSeek R1 Zero

DeepSeek

DeepSeek R1 Zero is a language model developed by DeepSeek. It achieves strong performance with an average score of 76.5% across 4 benchmarks. It excels particularly in MATH-500 (95.9%), AIME 2024 (86.7%), GPQA (73.3%). It's licensed for commercial use, making it suitable for enterprise applications. Released in 2025, it represents DeepSeek's latest advancement in AI technology.

DeepSeek R1 Distill Qwen 14B

DeepSeek

2025-01-20

DeepSeek R1 Zero

DeepSeek

2025-01-20

0 days newer

Average performance across 4 common benchmarks

DeepSeek R1 Distill Qwen 14B

Average Score:71.5%

DeepSeek R1 Zero

+5.0%

Average Score:76.5%

Performance comparison across key benchmark categories

DeepSeek R1 Distill Qwen 14B

math

93.9%

general

69.5%

code

+3.1%

53.1%

DeepSeek R1 Zero

math

+2.0%

95.9%

general

+10.5%

80.0%

code

50.0%

Benchmark Scores - Detailed View

Side-by-side comparison of all benchmark scores

Provider Availability & Performance

Available providers and their performance metrics

DeepSeek R1 Distill Qwen 14B

0 providers

DeepSeek R1 Zero

0 providers

DeepSeek R1 Distill Qwen 14B

Avg Score:71.5%

Providers:0

DeepSeek R1 Zero

+5.0%

Avg Score:76.5%

Providers:0