Skip to main content
ModelLLMsvDeepSeek-R1-0528

DeepSeek-R1

by DeepSeek · open-source · Last verified 2026-03-17

DeepSeek's reasoning-specialized model trained with reinforcement learning to produce detailed chain-of-thought before answering. Achieves performance competitive with OpenAI o1 on math and science benchmarks.

https://www.deepseek.com
B+
B+Good
Adoption: AQuality: A+Freshness: A+Citations: AEngagement: F

Specifications

License
MIT
Pricing
open-source
Capabilities
reasoning, chain-of-thought, math, code-generation, scientific-analysis, problem-solving
Integrations
huggingface, vllm, ollama, langchain
Use Cases
complex-reasoning, math-competitions, scientific-research, code-generation, logic-puzzles
API Available
Yes
Parameters
671B (37B active)
Context Window
128K tokens
Modalities
text
Training Cutoff
Late 2024
Tags
llm, open-source, reasoning, chain-of-thought, math, deepseek
Added
2026-03-17
Completeness
100%

Index Score

71.65
Adoption
80
Quality
92
Freshness
90
Citations
85
Engagement
0

Explore the full AI ecosystem on Agents as a Service