Skip to main content

DeepSeek R1 0528 (May '25)

DeepSeekDeepSeekOpen WeightMIT · Commercial OK

Description

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.

Release Date
2025-05-28
Parameters
671.0B
Context Length
164K
Modalities
text

Capability Radar

43
general
44
coding
83
reasoning
54
scienceest.
10
agents
0
multimodal

Science uses a reasoning proxy when dedicated science benchmarks are unavailable.

Rankings

Domain#RankScoreSource
Agents & Tools102
8.0
LS
Code Ranking129
53.0
AA
General Ranking198
50.0
AA
Math Reasoning65
85.0
AA
Reasoning95
36.0
LS
Science101
61.0
AA

Benchmark Scores (LLM Stats)

Agents

BrowseComp8.9%SR
Terminal-Bench5.7%SR

Biology

GPQA81.0%SR

Code

LiveCodeBench73.3%SR
Aider-Polyglot71.6%SR
SWE-Bench Verified44.6%SR
SWE-bench Multilingual30.5%SR

Factuality

SimpleQA92.3%SR

Finance

MMLU-Pro85.0%SR

General

MMLU-Redux93.4%SR

Math

AIME 202491.4%SR
AIME 202587.5%SR
HMMT 202579.4%SR
CodeForces0.64 / 3000SR
Humanity's Last Exam17.7%SR

Reasoning

BrowseComp-zh35.7%SR

AA Evaluation Indices

Math Index
76.0
Intelligence Index
27.1
Coding Index
24.0
Math 500
1.0
Aime
0.9
Mmlu Pro
0.8
Gpqa
0.8
Livecodebench
0.8
Aime 25
0.8
Lcr
0.5
Scicode
0.4
Ifbench
0.4
Tau2
0.4
Terminalbench Hard
0.2
Hle
0.1

LLM Stats Category Scores

Factuality
90
Language
90
Biology
80
Chemistry
80
Finance
80
General
80
Healthcare
80
Legal
80
Physics
80
Math
70
Reasoning
60
Code
50
Frontend Development
40
Vision
20
Search
20
Agents
10

Pricing

Input Price$1.35 / 1M tokens
Output Price$4.2 / 1M tokens
Blended Price (3:1)$2.063 / 1M tokens

Speed

Tokens/sec0.0 tokens/s
Time to First Token0.00s
Time to Answer0.00s

Available Providers

(LS internal units)
ProviderInput PriceOutput Price
DeepSeek550K2.2M
Novita700K2.5M

External Sources