llmboard.ai
Benchmarks
CompareRankings
llmboard.ai
Benchmarks
CompareRankings
HomeModelsDeepSeek-R1

DeepSeek model product

DeepSeek-R1

DeepSeek-R1-0528 is the May 28, 2025 version of DeepSeek's reasoning model. It features advanced thinking capabilities and serves as a benchmark comparison for newer models like DeepSeek-V3.1. This model excels in complex reasoning tasks, mathematical problem-solving, and code generation through its thinking mode approach.

Updated Aug 10, 2026. Default version: DeepSeek-R1-0528

Compare
LLMBoard score44.1DeepSeek-R1-0528
Coverage100%10 benchmark families
Context window131.1KTokens
Official input priceN/AOfficial price unavailable

On this page

  • Specification
  • Capability
  • Benchmarks
  • Arena
  • Pricing
  • Versions
  • About
  • Compare
  • Similar models
  • FAQ

Model specification

Structured fields from the published 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
No
License
MIT

Capability profile

This profile uses the latest version under this unique model that has a calculated LLMBoard score. Arena and price are excluded.

DeepSeek-R1-0528 category scores

Benchmark results

Published benchmark records for the scored version DeepSeek-R1-0528.

16 rows
Columns

Show columns

SimpleQA0.944693.3%CAug 7, 2026
Aider-Polyglot0.762276.2%CAug 7, 2026
AIME 20240.975388.5%CAug 7, 2026
MMLU-Redux0.9104880.8%CAug 7, 2026
BrowseComp-zh0.413130.0%CAug 7, 2026
CodeForces0.6141613.3%CAug 7, 2026
LiveCodeBench0.7177377.8%CAug 7, 2026
MMLU-Pro0.81712987.5%CAug 7, 2026
HMMT 20250.8253325.0%CAug 7, 2026
Terminal-Bench0.125250.0%CAug 7, 2026
SWE-bench Multilingual0.334340.0%CAug 7, 2026
AIME 20250.95511452.2%CAug 7, 2026
BrowseComp0.158580.0%CAug 7, 2026
Humanity's Last Exam0.2639231.9%CAug 7, 2026
GPQA0.88023366.0%CAug 7, 2026
SWE-Bench Verified0.49110412.6%CAug 7, 2026

Arena results

Preference and agent-evaluation signals from published Arena datasets.

58 rows
Columns

Show columns

textcreative writing641409.52,427N/AAug 6, 2026
textpolish641430.81,966N/AAug 6, 2026
textindustry medicine and healthcare681446.61,242N/AAug 6, 2026
textjapanese721383.8548N/AAug 6, 2026
textindustry entertainment and sports and media751401.73,203N/AAug 6, 2026
textrussian751425.11,248N/AAug 6, 2026
textoverall791428.018,422N/AAug 6, 2026
textexclude ties791420.313,274N/AAug 6, 2026
textnon english791415.39,552N/AAug 6, 2026
text style controljapanese801383.3548N/AAug 6, 2026
textenglish891434.38,864N/AAug 6, 2026
textindustry writing and literature and language911402.94,222N/AAug 6, 2026
textchinese931460.21,005N/AAug 6, 2026
text style controlpolish961414.21,966N/AAug 6, 2026
text style controlrussian981414.61,248N/AAug 6, 2026
text style controlcreative writing1011393.52,427N/AAug 6, 2026
text style controlindustry medicine and healthcare1011443.01,242N/AAug 6, 2026
textindustry life and physical and social science1031430.83,424N/AAug 6, 2026
text style controlexclude ties1051412.913,274N/AAug 6, 2026
text style controlindustry software and it services1051455.95,670N/AAug 6, 2026
textfrench1061420.2206N/AAug 6, 2026
text style controloverall1061422.118,422N/AAug 6, 2026
text style controlindustry entertainment and sports and media1061389.73,203N/AAug 6, 2026
text style controlnon english1061405.89,552N/AAug 6, 2026
textgerman1071397.8560N/AAug 6, 2026
textindustry legal and government1081419.81,388N/AAug 6, 2026
textindustry mathematical1081418.9943N/AAug 6, 2026
textindustry software and it services1081435.45,670N/AAug 6, 2026
textspanish1081406.1230N/AAug 6, 2026
text style controlcoding1081464.42,725N/AAug 6, 2026
text style controlenglish1081431.78,864N/AAug 6, 2026
textkorean1131353.9295N/AAug 6, 2026
textindustry business and management and financial operations1151399.62,884N/AAug 6, 2026
text style controlhard prompts1151433.56,948N/AAug 6, 2026
textcoding1161427.02,725N/AAug 6, 2026
texthard prompts1171415.96,948N/AAug 6, 2026
text style controlchinese1181446.81,005N/AAug 6, 2026
text style controlkorean1181347.7295N/AAug 6, 2026
text style controlfrench1201422.4206N/AAug 6, 2026
text style controlindustry mathematical1201415.2943N/AAug 6, 2026
text style controlspanish1201395.9230N/AAug 6, 2026
textmulti turn1211405.32,954N/AAug 6, 2026
text style controlindustry writing and literature and language1211390.14,222N/AAug 6, 2026
text style controlhard prompts english1221438.53,490N/AAug 6, 2026
texthard prompts english1241417.63,490N/AAug 6, 2026
text style controlgerman1261384.4560N/AAug 6, 2026
text style controlindustry legal and government1271415.21,388N/AAug 6, 2026
text style controlindustry life and physical and social science1271425.63,424N/AAug 6, 2026
textmath1281403.2863N/AAug 6, 2026
textinstruction following1291382.04,046N/AAug 6, 2026
text style controlindustry business and management and financial operations1291404.22,884N/AAug 6, 2026
text style controlexpert1311419.9881N/AAug 6, 2026
text style controlmulti turn1321405.72,954N/AAug 6, 2026
textexpert1341396.7881N/AAug 6, 2026
text style controlinstruction following1341391.64,046N/AAug 6, 2026
text style controllonger query1371407.03,130N/AAug 6, 2026
textlonger query1381391.23,130N/AAug 6, 2026
text style controlmath1431396.1863N/AAug 6, 2026

Pricing

Official vendor API PAYG pricing is summarized first. The table then lists individual provider offerings without treating their minimum as the official price.

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
11 rows
Columns

Show columns

NanoGPTdeepseek-ai/DeepSeek-R1-0528global$0.40$1.7128KAug 7, 2026
submodeldeepseek-ai/DeepSeek-R1-0528global$0.50$2.1575KAug 7, 2026
Deep Infradeepseek-ai/DeepSeek-R1-0528global$0.50$2.15163.8KAug 7, 2026
Meganovadeepseek-ai/DeepSeek-R1-0528global$0.50$2.15163.8KAug 7, 2026
Alibaba (China)deepseek-r1-0528global$0.574$2.29131.1KAug 7, 2026
Cortecsdeepseek-r1-0528global$0.652$2.57164KAug 7, 2026
TensorXdeepseek/deepseek-r1-0528global$0.66$2.6164KAug 7, 2026
Kilo Gatewaydeepseek/deepseek-r1-0528global$0.70$2.5163.8KAug 7, 2026
NovitaAIdeepseek/deepseek-r1-0528global$0.70$2.5163.8KAug 7, 2026
Jiekou.AIdeepseek/deepseek-r1-0528global$0.70$2.5163.8KAug 7, 2026
Hugging Facedeepseek-ai/DeepSeek-R1-0528global$3$5163.8KAug 7, 2026

Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.

DeepSeek-R1 versions

All published versions linked to this unique model. The score columns identify the version used by the current overall ranking.

3 rows
Columns

Show columns

DeepSeek-R1-0528May 28, 202544.1671B131.1K131.1KNoMIT
DeepSeek-R1Jan 20, 2025N/A671B128K32.8KYesMIT
DeepSeek R1 ZeroJan 20, 2025N/A671BN/AN/ANoMIT

What is DeepSeek-R1?

A concise description based on the published model registry.

DeepSeek-R1-0528 is the May 28, 2025 version of DeepSeek's reasoning model. It features advanced thinking capabilities and serves as a benchmark comparison for newer models like DeepSeek-V3.1. This model excels in complex reasoning tasks, mathematical problem-solving, and code generation through its thinking mode approach.

Use the benchmark, Arena and pricing sections above as separate evidence. A missing field means the current data snapshot does not support that claim.

Data snapshot: 2026-08-07. Editorial model content is not available in the backend.

DeepSeek-R1 vs nearby models

Open a comparison with the three ranked models immediately above and below this model.

DeepSeek-R1vsGranite 3.3 8BDeepSeek-R1vsMiniMax M2DeepSeek-R1vsLlama 3.1 Nemotron Nano 8BDeepSeek-R1vsQwen2.5 14BDeepSeek-R1vsLlama 3.1 Nemotron 70BDeepSeek-R1vsMistral Small 3.1 24B

Models similar to DeepSeek-R1

Recommendations prioritize the same model type and family, then the closest published LLMBoard score.

#119-6.0
DE

DeepSeek-V3

DeepSeek

38.1 LLMBoard

DetailsCompare
#126-8.1
DE

DeepSeek-V3.1

DeepSeek

36.0 LLMBoard

DetailsCompare
#32+25.4
DE

DeepSeek-V2.5

DeepSeek

69.5 LLMBoard

DetailsCompare
#28+27.6
DE

DeepSeek-V4-Flash

DeepSeek

71.7 LLMBoard

DetailsCompare
#18+31.4
DE

DeepSeek-V3.2

DeepSeek

75.5 LLMBoard

DetailsCompare
#12+36.0
DE

DeepSeek-V4-Pro

DeepSeek

80.1 LLMBoard

DetailsCompare

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 is published under DeepSeek in the model registry.

What is the context window for DeepSeek-R1?

The default version has a 131.1K token context window.

Is DeepSeek-R1 open weight?

No. The default version is not marked as having publicly available weights.

How many API providers offer DeepSeek-R1?

12 published provider offerings are linked to the default version.

What models should I compare DeepSeek-R1 with?

Nearby ranked alternatives include Granite 3.3 8B, MiniMax M2, Llama 3.1 Nemotron Nano 8B.

Rankings

OverallCodingText ArenaPricing

Modalities

Image GenerationVideo GenerationSpeech-to-TextEmbeddings

Benchmarks

All BenchmarksReasoningMathCoding

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai