DeepSeek model product
DeepSeek-R1
DeepSeek-R1 is a reasoning model for complex reasoning, mathematical problem-solving, and code generation through a thinking mode approach.
Updated Sep 8, 2026. Default version: DeepSeek-R1-0528
LLMBoard Score42.6DeepSeek-R1-0528
Coverage80%16 benchmark families
Context window131.1KTokens
Official input priceN/AOfficial price unavailable
DeepSeek-R1 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
DeepSeek-R1 Benchmark Results
Benchmark scores for DeepSeek-R1-0528.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkSimpleQA | Score92.30% | Rank04 | Participants47 | Percentile93.48% | EvidenceC | Evaluated |
| BenchmarkAider-Polyglot | Score71.60% | Rank06 | Participants22 | Percentile76.19% | EvidenceC | Evaluated |
| BenchmarkAIME 2024 | Score91.40% | Rank07 | Participants53 | Percentile88.46% | EvidenceC | Evaluated |
| BenchmarkMMLU-Redux | Score93.40% | Rank10 | Participants48 | Percentile80.85% | EvidenceC | Evaluated |
| BenchmarkBrowseComp-zh | Score35.70% | Rank13 | Participants13 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkCodeForces | Score64.33% | Rank15 | Participants17 | Percentile12.50% | EvidenceC | Evaluated |
| BenchmarkLiveCodeBench | Score73.30% | Rank19 | Participants75 | Percentile75.68% | EvidenceC | Evaluated |
| BenchmarkMMLU-Pro | Score85.00% | Rank20 | Participants138 | Percentile86.13% | EvidenceC | Evaluated |
| BenchmarkHMMT 2025 | Score79.40% | Rank25 | Participants33 | Percentile25.00% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench | Score5.70% | Rank25 | Participants25 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkSWE-bench Multilingual | Score30.50% | Rank43 | Participants43 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkAIME 2025 | Score87.50% | Rank57 | Participants119 | Percentile52.54% | EvidenceC | Evaluated |
| BenchmarkBrowseComp | Score8.90% | Rank63 | Participants63 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text | Score1,427.38 rating | Rank70 | Participants210 | Percentile66.99% | EvidenceA | Evaluated |
| BenchmarkHumanity's Last Exam | Score17.70% | Rank73 | Participants103 | Percentile29.41% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,421.34 rating | Rank88 | Participants210 | Percentile58.37% | EvidenceA | Evaluated |
| BenchmarkGPQA | Score81.00% | Rank89 | Participants247 | Percentile64.23% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Verified | Score44.60% | Rank100 | Participants113 | Percentile11.61% | EvidenceC | Evaluated |
DeepSeek-R1 Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext | Categorycreative writing | Rank56 | Rating / score1,405.74 | Votes2,391 | ObservationsN/A | Result date |
| Arenatext | Categoryjapanese | Rank56 | Rating / score1,393.54 | Votes607 | ObservationsN/A | Result date |
| Arenatext style control | Categoryjapanese | Rank60 | Rating / score1,392.31 | Votes607 | ObservationsN/A | Result date |
| Arenatext | Categorypolish | Rank61 | Rating / score1,428.23 | Votes1,977 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry entertainment and sports and media | Rank63 | Rating / score1,400.96 | Votes3,168 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry medicine and healthcare | Rank65 | Rating / score1,444.23 | Votes1,227 | ObservationsN/A | Result date |
| Arenatext | Categoryrussian | Rank68 | Rating / score1,421.82 | Votes1,521 | ObservationsN/A | Result date |
| Arenatext | Categoryexclude ties | Rank69 | Rating / score1,419.22 | Votes13,040 | ObservationsN/A | Result date |
| Arenatext | Categoryoverall | Rank70 | Rating / score1,427.38 | Votes18,092 | ObservationsN/A | Result date |
| Arenatext | Categorynon english | Rank72 | Rating / score1,411.43 | Votes9,954 | ObservationsN/A | Result date |
| Arenatext | Categoryenglish | Rank73 | Rating / score1,436.88 | Votes8,132 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry writing and literature and language | Rank76 | Rating / score1,401.44 | Votes4,170 | ObservationsN/A | Result date |
| Arenatext style control | Categorypolish | Rank79 | Rating / score1,411.57 | Votes1,977 | ObservationsN/A | Result date |
| Arenatext | Categorygerman | Rank81 | Rating / score1,404.58 | Votes592 | ObservationsN/A | Result date |
| Arenatext | Categorykorean | Rank82 | Rating / score1,358.46 | Votes321 | ObservationsN/A | Result date |
| Arenatext style control | Categoryrussian | Rank82 | Rating / score1,412.28 | Votes1,521 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry medicine and healthcare | Rank84 | Rating / score1,441.01 | Votes1,227 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry life and physical and social science | Rank86 | Rating / score1,430.57 | Votes3,377 | ObservationsN/A | Result date |
| Arenatext style control | Categoryenglish | Rank87 | Rating / score1,433.34 | Votes8,132 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry entertainment and sports and media | Rank87 | Rating / score1,389.06 | Votes3,168 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry software and it services | Rank88 | Rating / score1,434.70 | Votes5,510 | ObservationsN/A | Result date |
| Arenatext style control | Categorycreative writing | Rank88 | Rating / score1,389.67 | Votes2,391 | ObservationsN/A | Result date |
| Arenatext style control | Categoryexclude ties | Rank88 | Rating / score1,411.76 | Votes13,040 | ObservationsN/A | Result date |
| Arenatext style control | Categoryoverall | Rank88 | Rating / score1,421.34 | Votes18,092 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry software and it services | Rank89 | Rating / score1,455.70 | Votes5,510 | ObservationsN/A | Result date |
| Arenatext | Categoryspanish | Rank90 | Rating / score1,408.57 | Votes260 | ObservationsN/A | Result date |
| Arenatext style control | Categorycoding | Rank90 | Rating / score1,463.99 | Votes2,686 | ObservationsN/A | Result date |
| Arenatext style control | Categorynon english | Rank90 | Rating / score1,402.98 | Votes9,954 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry business and management and financial operations | Rank91 | Rating / score1,401.28 | Votes2,845 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry legal and government | Rank91 | Rating / score1,419.33 | Votes1,371 | ObservationsN/A | Result date |
DeepSeek-R1 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- From $0.40 input, $1.7 output per 1M via NanoGPT
- Tracked offerings
- 12
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderNanoGPT | Provider model IDdeepseek-ai/DeepSeek-R1-0528 | Regionglobal | Input / 1M$0.40 | Output / 1M$1.7 | Context163.8K | Updated |
| ProviderMeganova | Provider model IDdeepseek-ai/DeepSeek-R1-0528 | Regionglobal | Input / 1M$0.50 | Output / 1M$2.15 | Context163.8K | Updated |
| ProviderDeep Infra | Provider model IDdeepseek-ai/DeepSeek-R1-0528 | Regionglobal | Input / 1M$0.50 | Output / 1M$2.15 | Context163.8K | Updated |
| Providersubmodel | Provider model IDdeepseek-ai/DeepSeek-R1-0528 | Regionglobal | Input / 1M$0.50 | Output / 1M$2.15 | Context75K | Updated |
| ProviderAlibaba (China) | Provider model IDdeepseek-r1-0528 | Regionglobal | Input / 1M$0.574 | Output / 1M$2.29 | Context131.1K | Updated |
| ProviderCortecs | Provider model IDdeepseek-r1-0528 | Regionglobal | Input / 1M$0.652 | Output / 1M$2.57 | Context164K | Updated |
| ProviderTensorX | Provider model IDdeepseek/deepseek-r1-0528 | Regionglobal | Input / 1M$0.66 | Output / 1M$2.6 | Context164K | Updated |
| ProviderJiekou.AI | Provider model IDdeepseek/deepseek-r1-0528 | Regionglobal | Input / 1M$0.70 | Output / 1M$2.5 | Context163.8K | Updated |
| ProviderNovitaAI | Provider model IDdeepseek/deepseek-r1-0528 | Regionglobal | Input / 1M$0.70 | Output / 1M$2.5 | Context163.8K | Updated |
| ProviderKilo Gateway | Provider model IDdeepseek/deepseek-r1-0528 | Regionglobal | Input / 1M$0.70 | Output / 1M$2.5 | Context163.8K | Updated |
| ProviderHugging Face | Provider model IDdeepseek-ai/DeepSeek-R1-0528 | Regionglobal | Input / 1M$3 | Output / 1M$5 | Context163.8K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
DeepSeek-R1 Runtime Performance
Provider-specific output speed and catalog latency for DeepSeek-R1-0528. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderDeepInfra | Output Speed45.04 tok/s | Catalog Latency0.61 s | Max Input131.1K | Max Output131.1K | Updated |
| ProviderDeepSeek | Output Speed9.00 tok/s | Catalog Latency0.30 s | Max Input131.1K | Max Output131.1K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
DeepSeek-R1 Specifications
Technical details for the model's default version.
- Version
- DeepSeek-R1-0528
- Released
- May 28, 2025
- Knowledge cutoff
- Unknown
- Parameters
- 671B
- Context window
- 131.1K
- Max output
- 131.1K
- Inputs
- text
- Outputs
- text
- Open weights
- Yes
- License
- MIT
DeepSeek-R1 Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionDeepSeek-R1-0528 | Released | LLMBoard42.65 | Parameters671B | Context131.1K | Max output131.1K | Open weightsYes | LicenseMIT |
| VersionDeepSeek R1 Zero | Released | LLMBoardN/A | Parameters671B | ContextN/A | Max outputN/A | Open weightsYes | LicenseMIT |
| VersionDeepSeek-R1 | Released | LLMBoardN/A | Parameters671B | Context131.1K | Max output131.1K | Open weightsYes | LicenseMIT |
Models similar to DeepSeek-R1
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
DE
DeepSeek-V3.1
DeepSeek
DE
DeepSeek-V3.2
DeepSeek
DE
DeepSeek-V3
DeepSeek
DE
DeepSeek-R1-Distill-Qwen
DeepSeek
DE
DeepSeek-V2.5
DeepSeek
DE
DeepSeek-R1-Distill-Llama
DeepSeek
What is DeepSeek-R1?
Key information about DeepSeek-R1 and its available data.
DeepSeek-R1 is DeepSeek's reasoning model, with DeepSeek-R1-0528 identified as its May 28, 2025 version. 1.
Data as of 2026-09-08.
FAQ
Common questions about DeepSeek-R1.
When was DeepSeek-R1 released?
DeepSeek-R1's default version was released on May 28, 2025.
How much does DeepSeek-R1 cost?
No official standard PAYG price is currently available for DeepSeek-R1. The lowest tracked third-party offer starts at $0.40 input and $1.7 output via NanoGPT.
Who created DeepSeek-R1?
DeepSeek-R1 was created by DeepSeek.
What is the context window for DeepSeek-R1?
The default version has a 131.1K token context window.
Is DeepSeek-R1 open weight?
Yes. The default version is marked as open weight under MIT.
How many API providers offer DeepSeek-R1?
12 provider offerings are linked to the default version.