DeepSeek R1
Open-weights reasoning model that matches o1 at 1/25 the price.
Intelligence index
73/ 100
vs all models68th pctile
Composite of MMLU, GPQA, MATH & HumanEval
Speed
60tok/s
vs all models18th pctile
Median across providers, steady state
Blended price
$0.96/ 1M tokens
vs all models64th pctile
3:1 input:output blend
At a glance
- Context window
- 128k tokens
- Max output
- 33k tokens
- Input price
- $0.55 / 1M tokens
- Output price
- $2.19 / 1M tokens
- Time to first token
- 1.5s
- Input modalities
- text
- Output modalities
- text
- License
- Open source
- Provider
- DeepSeek
Benchmark scores
Public scores from each provider; bars compare this model against the leader in each benchmark.
MMLU
General knowledge across 57 subjects
87.1
leader: 91.8
MMLU Pro
Harder MMLU successor with more reasoning
75.9
leader: 80.0
GPQA
Graduate-level science Q&A
71.5
leader: 78.0
MATH
Competition mathematics
90.2
leader: 94.8
HumanEval
Python code generation pass@1
91.0
leader: 95.8
Strengths
- Reasoning at GPT-class scores
- Open weights
- Cheap
Weaknesses
- Slower than non-reasoning peers
Best for
- Self-hosted reasoning
- Math & code
- Cost-sensitive agents
Models you should also evaluate
DeepSeek
DeepSeek V3
Frontier-class quality at fast-tier prices — and open weights.
67 intel90 tok/s$0.48 /1M
OpenAI
GPT-5.5
OpenAI’s 2026 flagship — strongest at reasoning, coding and tool use.
82 intel95 tok/s$7.50 /1M
Anthropic
Claude 4 Opus
Anthropic’s 2026 flagship — best-in-class on code and long-horizon agents.
81 intel50 tok/s$16.00 /1M
DeepSeek R1 vs… popular head-to-heads
One-click matchups against the models people compare DeepSeek R1 with most.
DeepSeek R1 — frequently asked questions
DeepSeek R1 is a large language model from DeepSeek, released on 20 January 2025. Open-weights reasoning model that matches o1 at 1/25 the price.
Need help choosing between models?
Compare every option in one sortable table — intelligence, speed and price on a single page.