Comprehensive side-by-side LLM comparison
DeepSeek-V3.1 leads with 25.4% higher average benchmark score. DeepSeek-V3.1 offers 166.9K more tokens in context window than o1-preview. DeepSeek-V3.1 is $73.73 cheaper per million tokens. Overall, DeepSeek-V3.1 is the stronger choice for coding tasks.
DeepSeek
DeepSeek-V3.1 was developed as an incremental advancement over DeepSeek-V3, designed to refine the mixture-of-experts architecture with improved training techniques. Built to enhance quality and efficiency while maintaining the open-source philosophy, it represents continued iteration on DeepSeek's flagship model line.
OpenAI
o1-preview was introduced as an early version of OpenAI's reasoning model series, designed to demonstrate the potential of AI models that engage in extended thinking before responding. Built to solve complex problems through deliberate reasoning processes, it represented an initial step toward more thoughtful and analytical AI systems.
4 months newer

o1-preview
OpenAI
2024-09-12

DeepSeek-V3.1
DeepSeek
2025-01-10
Cost per million tokens (USD)

DeepSeek-V3.1

o1-preview
Context window and performance specifications
Average performance across 4 common benchmarks

DeepSeek-V3.1

o1-preview
Performance comparison across key benchmark categories

DeepSeek-V3.1

o1-preview
Available providers and their performance metrics

DeepSeek-V3.1
DeepInfra
Novita

o1-preview

DeepSeek-V3.1

o1-preview

DeepSeek-V3.1

o1-preview
Azure
OpenAI