DeepSeek logo

R1

by DeepSeek · Released Jan 2025

Open Source
48.0
avg score
Rank #115
Compare
Better than 51% of all models
Context
64K tokens (~32 books)
Input $/1M
$0.70
Output $/1M
$2.50
Type
text
License
Open Source
Benchmarks
14 tested
Data updated today
About

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....

Tested on 14 benchmarks with 45.1% average. Top scores: Chatbot Arena Elo — Overall (1397.5%), MATH level 5 (93.0%), Lech Mazur Writing (83.0%).

Capabilities
coding
46.7
#78 globally
reasoning
11.4
#126 globally
math
73.2
#28 globally
knowledge
52.0
#90 globally
Benchmark Scores
Compare All
Tested on 14 benchmarks · Ranked across 5 categories
Score Distribution (all 233 models)
0255075100
▲ You are here
Aider polyglot

Multi-language code editing from Aider. Tests editing ability across Python, JavaScript, TypeScript, Java, C++, Go, Rust, and more.

56.9
WeirdML

Unusual and adversarial machine learning challenges. Tests robustness of reasoning about edge cases in ML systems.

36.5
SimpleBench

Deceptively simple questions that humans find easy but AI models often get wrong. Tests common sense and reasoning gaps.

17.1
ARC-AGI

Abstraction and Reasoning Corpus. Tests fluid intelligence through novel visual pattern recognition puzzles. Core measure of general intelligence.

15.8
ARC-AGI-2

ARC-AGI 2, harder sequel to ARC. More complex abstract reasoning patterns that test generalization ability beyond training data.

1.3
MATH level 5

Competition-level math from AMC, AIME, and olympiad problems. Level 5 is the hardest tier, requiring creative problem-solving.

93.0
OTIS Mock AIME 2024-2025

Mock AIME (American Invitational Mathematics Exam) problems from OTIS. Tests mathematical competition performance.

53.3
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Links
Documentation
Community
BenchGecko API
deepseek-r1
Specifications
  • Typetext
  • Context64K tokens (~32 books)
  • ReleasedJan 2025
  • LicenseOpen Source
  • StatusActive
  • Cost / Message~$0.004
Available On
DeepSeek logoDeepSeek$0.70
Share & Export
Tweet
R1 is an open-source text AI model by DeepSeek, released in January 2025. It has an average benchmark score of 48.0. Context window: 64K tokens.