About R1
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.
Fully open-source model & [technical report](https://api-docs.deepseek.com/news/news250120).
MIT licensed: Distill & commercialize freely!
Specifications
- Provider
- DeepSeek
- Context Length
- 163,840 tokens
- Input Types
- text
- Output Types
- text
- Category
- DeepSeek
- Added
- 1/20/2025
Benchmark Performance
How R1 compares to its closest rivals across industry benchmarks
Comprehensive comparison of AI models across intelligence, price, speed, and latency
Metric: Intelligence Index
#40
Qwen3 Next 80B A3B
54.0
#41
ERNIE 5.0 Thinking Preview
53.0
#43
gpt-oss-20B (high)
52.0
#44
Magistral Medium 1.2
52.0
#46
Qwen3 VL 32B
52.0
#47
NVIDIA Nemotron 3 Nano
52.0
#48
Seed-OSS-36B-Instruct
52.0
Frequently Asked Questions
Common questions about R1