Back to Models
deepseek logo
deepseek/deepseek-r1
Not Available

R1

DeepSeek R1 is here: Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass. Fully open-source model & [technical report](https://api-docs.deepseek.com/news/news250120). MIT licensed: Distill & commercialize freely!

1/20/2025
64,000 tokens
#60 Text (Korean)
Specifications

Modalities

Input
text
Output
text

Supported Parameters

frequency_penalty
include_reasoning
max_tokens
presence_penalty
reasoning
repetition_penalty
seed
stop
temperature
tool_choice
tools
top_k
top_p

Max Output Tokens

16,000
Leaderboard
Text
🏆OverallELO: 1,398
#91
🇯🇵JapaneseELO: 1,336
#66
🇨🇳ChineseELO: 1,430
#86
🇰🇷KoreanELO: 1,353
#60
🇬🇧EnglishELO: 1,412
#88
frenchELO: 1,392
#97
germanELO: 1,395
#64
spanishELO: 1,393
#77
russianELO: 1,380
#92
💻CodingELO: 1,444
#86
🧮MathELO: 1,410
#69
✍️Creative WritingELO: 1,374
#83
📝Instruction FollowingELO: 1,395
#81
🌶️Hard PromptsELO: 1,418
#91
💬Multi-TurnELO: 1,410
#75