Leaderboard · Model · Updated
DeepSeek R1
Open-weights reasoning model rivalling closed frontier models at a fraction of the price.
At a glance
| Provider | DeepSeek |
|---|---|
| Released | 2025-01 |
| Tier | open-weights |
| License | Open-weights (MIT) |
| Modalities | text |
| Context window | 128k tokens |
| Max output | 32.768k tokens |
| API price · input | $0.55 / 1M tokens |
| API price · output | $2.19 / 1M tokens |
| Hugging Face | deepseek-ai/DeepSeek-R1 |
Benchmark performance
How DeepSeek R1 stacks up against the current leader (GPT-5) and the median model in the leaderboard:
| Benchmark | DeepSeek R1 | GPT-5 | Median |
|---|---|---|---|
| Chatbot Arena Elo | 1357 | 1410 | 1320 |
| MMLU-Pro | 84.0 | 86.8 | 78.0 |
| GPQA Diamond | 71.5 | 87.3 | 65.0 |
| MATH | 97.3 | 96.7 | 78.3 |
| HumanEval | 92.0 | 95.1 | 92.0 |
| SWE-Bench Verified | 49.2 | 74.9 | 49.0 |
Numbers compiled from provider technical reports and Chatbot Arena. See methodology for the composite-score formula.
OpenRouter routes your requests across DeepSeek R1, GPT-5, Claude, Gemini, and 100+ other models behind a single API key — pay-as-you-go, no monthly minimum. Try OpenRouter → (affiliate · supports this site)
What does DeepSeek R1 cost in practice?
API pricing is $0.55 per 1M input tokens and $2.19 per 1M output tokens. Assuming a 50/50 input/output split, here is what that looks like at three workload sizes:
| Volume | Per day | Per month | Per year |
|---|---|---|---|
| 1M tokens/day | $1.37 | $41.10 | $500.05 |
| 10M tokens/day | $13.70 | $411.00 | $5,001 |
| 100M tokens/day | $137.00 | $4,110 | $50,005 |
Strengths & weaknesses
Where it shines
- MATH: 97.3 (rank #1 of 29, top tier)
- MMLU-Pro: 84.0 (rank #7 of 29, above average)
- HumanEval: 92.0 (rank #9 of 30, above average)
Where it lags
- SWE-Bench: 49.2 (rank #12 of 18, mid-pack)
Best alternatives
The closest models to DeepSeek R1 by tier and benchmark score:
| Model | Score | $ in / out | Context | Action |
|---|---|---|---|---|
| Phi-4 Microsoft |
71.2 | $0.07 / $0.14 | 16.384k | Try → · vs DeepSeek |
| Qwen2.5-Coder 32B Alibaba |
68.8 | $0.18 / $0.18 | 131.072k | Try → · vs DeepSeek |
| DeepSeek V3 DeepSeek |
68.0 | $0.27 / $1.10 | 128k | Try → · vs DeepSeek |
| Llama 3.1 405B Instruct Meta |
65.7 | $2.70 / $2.70 | 128k | Try → · vs DeepSeek |
| Qwen2.5 72B Instruct Alibaba |
65.6 | $0.35 / $0.40 | 131.072k | Try → · vs DeepSeek |
Frequently asked questions
Is DeepSeek R1 a good model?
DeepSeek R1 scores 75.4 on the llmrank.top composite (rank #11 of 30). It is competitive with the leaders (GPT-5 tops the board at 86.0). Whether it's the right fit depends on your workload — see the use-case discussion on this page.
How much does DeepSeek R1 cost?
DeepSeek R1 is priced at $0.55 per 1M input tokens and $2.19 per 1M output tokens (USD). For a 10M-token-per-day workload split 50/50, that works out to roughly $13.70/day or $5,001/year.
What is DeepSeek R1's context window?
128k tokens. For very long inputs, consider a 1M+ context model like Gemini 2.5 Pro or GPT-4.1.
Is DeepSeek R1 open source?
Yes — released under the MIT license, weights are downloadable from the provider or Hugging Face.
What is DeepSeek R1's SWE-Bench score?
DeepSeek R1 scores 49.2% on SWE-Bench Verified — the benchmark that measures real-world GitHub issue resolution. Its Chatbot Arena Elo is 1357.
What are the best alternatives to DeepSeek R1?
Closest alternatives by tier and score: Phi-4, Qwen2.5-Coder 32B, DeepSeek V3. See the alternatives section on this page for side-by-side numbers.
Related: Phi-4 · Qwen2.5-Coder 32B · DeepSeek V3 · Full leaderboard
Spotted out-of-date numbers? Open an issue — corrections usually ship within 24h.
Try DeepSeek R1 now
Direct link to the official playground — or use OpenRouter to A/B test it against any other model on a single API key.