Comprehensive side-by-side LLM comparison
DeepSeek-R1-0528 leads with 26.9% higher average benchmark score. DeepSeek-V3 is $1.28 cheaper per million tokens. DeepSeek-R1-0528 is available on 3 providers. Overall, DeepSeek-R1-0528 is the stronger choice for coding tasks.
DeepSeek
DeepSeek-R1-0528 represents a specific release iteration of the DeepSeek-R1 model, developed to incorporate refinements and improvements from ongoing training. Built to provide enhanced reasoning capabilities based on accumulated insights, it continues the evolution of DeepSeek's reasoning-focused architecture.
DeepSeek
DeepSeek-V3 was introduced as a major architectural advancement, developed with 671B mixture-of-experts parameters and trained on 14.8 trillion tokens. Built to be three times faster than V2 while maintaining open-source availability, it demonstrates competitive performance against frontier closed-source models and represents a significant leap in efficient large-scale model design.
5 months newer

DeepSeek-V3
DeepSeek
2024-12-25

DeepSeek-R1-0528
DeepSeek
2025-05-28
Cost per million tokens (USD)

DeepSeek-R1-0528

DeepSeek-V3
Context window and performance specifications
Average performance across 8 common benchmarks

DeepSeek-R1-0528

DeepSeek-V3
Performance comparison across key benchmark categories

DeepSeek-R1-0528

DeepSeek-V3
Available providers and their performance metrics

DeepSeek-R1-0528
DeepInfra
DeepSeek
Novita

DeepSeek-R1-0528

DeepSeek-V3

DeepSeek-R1-0528

DeepSeek-V3

DeepSeek-V3
DeepSeek