Model comparison

DeepSeek-R1-0528 vs o3

Capability radar, value bars, and side-by-side posture.

← Back to Compare

DeepSeek-R1-0528
Not scored
value score
o3
93
value score
DeepSeek-R1-0528 ctx
128K
o3 ctx
200K

Capability radar

Value · context · multimodal · openness · speed posture

Value head-to-head

  • o393

Attribute tape

FieldDeepSeek-R1-0528o3
Developerdeepseek-aiOpenAI
Context128K200K
ModalitiesText, Code
OpennessOpen WeightsProprietary Model
Speed
Price$10/1M in · $40/1M out
Value score93
SummaryDeepSeek-R1-0528 is an updated open-weight reasoning LLM from DeepSeek, built on a Mixture-of-Experts backbone and optimized for math, code, tool use, and multi-step problem solving. It is a checkpoint upgrade over the original R1, with reported improvements in reasoning depth, hallucination reduction, and function-calling accuracy.OpenAI reasoning model focused on hard problems.
Open DeepSeek-R1-0528Open o3