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
71.65Adoption
80
Quality
92
Freshness
90
Citations
85
Engagement
0