R1
DeepSeek · released Jan 20, 2025
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....
Specification
- Context window
- 164K
- Max output
- 16K
- Knowledge cutoff
- Jul 31, 2024
- Parameters
- 684.5B
- Licence
- mit
- Serving providers
- 2
- Moderated
- No
- Uptime
- 100.0%
Intelligence
20.4
60th percentile
Coding
—
Coding Index
Agentic
3.1
Agentic Index
Output speed
22 t/s
Median across providers
Latency
956ms
Time to first token
Cost per task
$0.24
Estimated
Benchmarks
Where the score comes from
The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.
Evaluation scores
Percentage correct · higher is better
- MMLU-Pro84.9%
- GPQA Diamond81.3%
- LiveCodeBench77.0%
- AIME 202576.0%
- AA-LCR (long context)56.7%
- SciCode40.3%
- IFBench39.6%
- τ²-bench (Telecom)36.5%
- Terminal-Bench Hard15.9%
- Humanity's Last Exam15.8%
An evaluation missing from this list was not run for this model — it is not a zero.
View as table
| Evaluation | Score |
|---|---|
| MMLU-Pro | 84.9% |
| GPQA Diamond | 81.3% |
| LiveCodeBench | 77.0% |
| AIME 2025 | 76.0% |
| AA-LCR (long context) | 56.7% |
| SciCode | 40.3% |
| IFBench | 39.6% |
| τ²-bench (Telecom) | 36.5% |
| Terminal-Bench Hard | 15.9% |
| Humanity's Last Exam | 15.8% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- Qwen3 Coder NextQwen21.3
- R1DeepSeek20.4
- North Mini Code (free)Cohere20.2
- GPT-5 NanoOpenAI20.1
- GLM 4.5Z.ai19.7
- Kimi K2 0711Moonshot AI19.7
- GPT-4.1OpenAI19.6
- o3 MiniOpenAI19.2
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| Qwen3 Coder Next | 21.3 |
| R1 | 20.4 |
| North Mini Code (free) | 20.2 |
| GPT-5 Nano | 20.1 |
| GLM 4.5 | 19.7 |
| Kimi K2 0711 | 19.7 |
| GPT-4.1 | 19.6 |
| o3 Mini | 19.2 |
Percentile among all indexed models
Pricing
What it costs to run
List prices per million tokens, plus what one representative task works out to.
List price
- Input / 1M tokens
- $0.7
- Output / 1M tokens
- $2.5
- Cached input / 1M
- Not offered
- Blended 3:1
- $1.15
One task, estimated
$0.24
- Input tokens
- 50,000
- Output tokens
- 80,000
- Profile
- Reasoning
Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).