Model comparison

DeepSeek V3.1 vs DeepSeek R1

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

← Back to Compare

DeepSeek V3.1
Not scored
value score
DeepSeek R1
90
value score
DeepSeek V3.1 ctx
DeepSeek R1 ctx
128K

Capability radar

Value · context · multimodal · openness · speed posture

Value head-to-head

  • DeepSeek R190

Attribute tape

FieldDeepSeek V3.1DeepSeek R1
Developer~deepseek~deepseek
Context128K
ModalitiesText, Code
OpennessOpen Weights
Speed
Price
Value score90
SummaryDeepSeek V3.1 is a hybrid large language model that unifies step-by-step reasoning ('Think' mode) and fast direct answering ('Non-Think' mode) in a single open-weight model, with a 1M-token context window and enhanced tool-use and agent capabilities.Reasoning-focused open-weights DeepSeek model.
Open DeepSeek V3.1Open DeepSeek R1