NEWHow AI models draw the world map · Gecko Tests
Beta
Home/Models/R1
DeepSeek logo

R1

by DeepSeek · Released Jan 2025

Open Source
46.0
avg score
Rank #167
Compare
Better than 46% of all models
Context
64K tokens (~32 books)
Input $/1M
$0.70
Output $/1M
$2.50
Type
text
License
Open Source
Benchmarks
15 tested
Data as of
About

DeepSeek R1 is here: Performance on par with 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 15 benchmarks · BenchGecko score 46.0. Top scores: Chatbot Arena Elo — Overall (1398.1%), MATH level 5 (93.0%), Lech Mazur Writing (83.0%).

Looking for similar performance at lower cost?
gpt-oss-120b scores 46.7 (102% as good) at $0.04/1M input · 95% cheaper
Capabilities
coding
46.7
#109 globally
reasoning
11.4
#168 globally
math
73.2
#39 globally
knowledge
52.0
#110 globally
general
51.9
#28 globally
Benchmark Scores
Compare All
Tested on 15 benchmarks · Ranked across 6 categories
Score Distribution (all 312 models)
0255075100
▲ You are here
codingCompare coding →
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·
reasoningCompare reasoning →
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·
mathCompare math →
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·
Quick compare:Alibaba Qwen logovs Qwen3.8 27BNVIDIA logovs Nemotron 3 UltraAlibaba Qwen logovs Qwen3.6 Flash
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Similar Models
Alibaba Qwen logo
Qwen3.8 27B
Alibaba Qwen
45.6$0.42/1M
NVIDIA logo
Nemotron 3 Ultra
NVIDIA
45.6$0.50/1M
Alibaba Qwen logo
Qwen3.6 Flash
Alibaba Qwen
46.6$0.19/1M
Links
Info
DeepSeekPricing explorerDevelopers · API
Research
Technical Report
Documentation
API DocsPlayground
Community
@DeepSeek
Source Code
GitHubHugging Face
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
Categories
codingreasoningmathknowledgegeneral
Learn More
transformeropen weightstokens
Share & Export
Tweet
Related Models
Alibaba Qwen logoQwen3.8 27B
45.6
NVIDIA logoNemotron 3 Ultra
45.6
Alibaba Qwen logoQwen3.6 Flash
46.6
z-ai logoGLM 5V Turbo
46.6
R1 is an open-source text AI model by DeepSeek, released in January 2025. It has an average benchmark score of 46.0. Context window: 64K tokens.

Related Models

Qwen3.8 27B · Alibaba QwenNemotron 3 Ultra · NVIDIAQwen3.6 Flash · Alibaba QwenGLM 5V Turbo · z-aigpt-oss-120b · OpenAI

Benchmarks

Chatbot Arena Elo — OverallMATH level 5Lech Mazur WritingFiction.LiveBenchGPQA diamond

Related Pages

DeepSeek · ProviderDeepSeek · EconomyAll ModelsCompare ModelsPricingDevelopers · API

Key facts · as of 2026-10-05

  • R1 by DeepSeek. BenchGecko score 46.0, rank 167 of 312 scored models (normalized average of public benchmark scores).
  • List price $0.70 input · $2.50 output per 1M tokens (as of 2026-10-05).
  • Sold by 1 provider (as of 2026-10-05): Novita (fp8) $0.70 in / $2.50 out.

How to cite · data as of 2026-10-05

R1 · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/deepseek-r1

Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP