DeepSeek
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!
- Input / 1M tokens
- $0.700
- Output / 1M tokens
- $2.50
- Context window
- 64K tokens
- Provider
- DeepSeek
- Knowledge cutoff
- 2024-07-31
Performance
Median streaming throughput and first-token latency measured by Artificial Analysis.
- Output tokens / sec
- 0 t/s
- Time to first token
- 0.00s
Benchmarks
Intelligence, coding, and math indexes plus the underlying evaluation scores.
- Intelligence Index
- 27
- Coding Index
- 24
- Math Index
- 76
- MMLU-Pro
- 84.9%
- GPQA
- 81.3%
- HLE
- 14.9%
- LiveCodeBench
- 77.0%
- SciCode
- 40.3%
- MATH-500
- 98.3%
- AIME
- 89.3%
Benchmarks via Artificial Analysis