Model Comparison
Comprehensive side-by-side analysis of model capabilities and performance
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-V3.1
DeepSeek
DeepSeek-V3.1 is a language model developed by DeepSeek. The model shows competitive results across 16 benchmarks. It excels particularly in SimpleQA (93.4%), MMLU-Redux (91.8%), MMLU-Pro (83.7%). The model shows particular specialization in factuality tasks with an average performance of 92.6%. It supports a 328K token context window for handling large documents. The model is available through 2 API providers. 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-V3.1
DeepSeek
2025-01-10
DeepSeek R1 Zero
DeepSeek
2025-01-20
10 days newer
Performance Metrics
Context window and performance specifications
DeepSeek R1 Zero
DeepSeek-V3.1
Average performance across 2 common benchmarks
DeepSeek R1 Zero
DeepSeek-V3.1
Performance comparison across key benchmark categories
DeepSeek R1 Zero
DeepSeek-V3.1
Provider Availability & Performance
Available providers and their performance metrics
DeepSeek R1 Zero
DeepSeek-V3.1
DeepInfra
Novita
DeepSeek R1 Zero
DeepSeek-V3.1