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 45.3. Top scores: Chatbot Arena Elo · Overall (1398.1%), MATH level 5 (93.0%), Lech Mazur Writing (83.0%).
gpt-oss-20b scores 45.0 (99% as good) at $0.03/1M input · 96% cheaper
Multi-language code editing from Aider. Tests editing ability across Python, JavaScript, TypeScript, Java, C++, Go, Rust, and more.
Unusual and adversarial machine learning challenges. Tests robustness of reasoning about edge cases in ML systems.
Deceptively simple questions that humans find easy but AI models often get wrong. Tests common sense and reasoning gaps.
Abstraction and Reasoning Corpus. Tests fluid intelligence through novel visual pattern recognition puzzles. Core measure of general intelligence.
ARC-AGI 2, harder sequel to ARC. More complex abstract reasoning patterns that test generalization ability beyond training data.
Competition-level math from AMC, AIME, and olympiad problems. Level 5 is the hardest tier, requiring creative problem-solving.
Mock AIME (American Invitational Mathematics Exam) problems from OTIS. Tests mathematical competition performance.
- Typetext
- Context64K tokens (~32 books)
- ReleasedJan 2025
- LicenseOpen Source
- StatusActive
- Cost / Message~$0.004
Frequently Asked Questions
Key facts · as of 2026-10-19
- R1 by DeepSeek. BenchGecko score 45.3, rank 179 of 326 scored models (normalized average of public benchmark scores).
- List price $0.70 input · $2.50 output per 1M tokens (as of 2026-10-19).
How to cite · data as of 2026-10-19
R1 · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-19. 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