Home/Models/deepseek-r3
ReasoningOpen WeightsOpen WeightsReasoningMath

DeepSeek R3

by DeepSeek · Open-weights reasoning powerhouse.

Visit website ↗
RAI ScoreS+Titan
950/ 1000
↑ 72RAI7dMethodology
Composite of 8 signals · 2,481 contributors

// Live community signal

Rate this model

4.75
RAI · live
Sign in to cast your signal →

About

Open R-series successor , frontier reasoning, open weights.

Dimension Scores

intelligence94
creativity78
accuracy94
speed52
coding94
research92
value100
safety80

Pros

  • +Open weights frontier reasoning
  • +Cheap

Cons

  • Slower than hosted o5

Community Reviews

Reviews open once this model is indexed in the live database.

Similar AIs