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
#98 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
๐Ÿ†OverallELO: 1,398
#132
๐Ÿ‡ฏ๐Ÿ‡ตJapaneseELO: 1,339
#111
๐Ÿ‡จ๐Ÿ‡ณChineseELO: 1,428
#132
๐Ÿ‡ฐ๐Ÿ‡ทKoreanELO: 1,357
#98
๐Ÿ‡ฌ๐Ÿ‡งEnglishELO: 1,413
#129
frenchELO: 1,390
#144
germanELO: 1,398
#101
spanishELO: 1,395
#114
russianELO: 1,381
#139
๐Ÿ’ปCodingELO: 1,445
#129
๐ŸงฎMathELO: 1,412
#110
โœ๏ธCreative WritingELO: 1,374
#124
๐Ÿ“Instruction FollowingELO: 1,397
#122
๐ŸŒถ๏ธHard PromptsELO: 1,419
#130
๐Ÿ’ฌMulti-TurnELO: 1,410
#118