DE

DeepSeek-R1-0528

Reasoning modelDeepSeek R1DeepSeek R1

DeepSeek-R1-0528

Release date: 2025-05-28Updated: 2025-08-08 15:46:412,664
Parameters
671B
Context length
64K
Chinese support
Supported
Reasoning ability

DeepSeek-R1-0528 is an AI model published by DeepSeek-AI, released on 2025-05-28, for Reasoning model, with 671B parameters, and 64K context length, requiring about 685GB storage, under the MIT License license, with a 98.00 score on MATH-500.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

DeepSeek-R1-0528

Model basics

Reasoning traces
Supported
Thinking modes
Thinking modes not supported
Context length
64K tokens
Max output length
64K tokens
Model type
Reasoning model
Modality (in / out)
Text → Text
Release date
2025-05-28
Model file size
685GB
MoE architecture
Yes
Total params / Active params
671B / 37B
Knowledge cutoff
No data
DeepSeek-R1-0528

Open source & experience

DeepSeek-R1-0528

Official resources

DataLearnerAI blog
No blog post yet
DeepSeek-R1-0528

API details

API speed
2/5
No public API pricing yet.
DeepSeek-R1-0528

Benchmark Results

DeepSeek-R1-0528 currently shows benchmark results led by MATH-500 (7 / 44, score 98), Creative Writing (4 / 23, score 86.25), MMLU Pro (25 / 126, score 85). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.

Thinking

General Knowledge

5 evaluations
Benchmark / mode
Score
Rank/total
85
25 / 126
81
70 / 179
21.20
54 / 65
17.70
113 / 159
1.30
52 / 59

Common Sense

1 evaluations
Benchmark / mode
Score
Rank/total
27.80
25 / 45

Coding and Software Engineer

2 evaluations
Benchmark / mode
Score
Rank/total
73.30
45 / 120
57.60
80 / 108

Math and Reasoning

5 evaluations
Benchmark / mode
Score
Rank/total
98
7 / 44
91.40
13 / 62
87.50
44 / 106

Writing and Creative Capabilities

1 evaluations
Benchmark / mode
Score
Rank/total
86.25
4 / 23

AI Agent - Tool Usage

1 evaluations
Benchmark / mode
Score
Rank/total
5.70
35 / 35

常识推理

1 evaluations
Benchmark / mode
Score
Rank/total
Simple Bench
Thinking Mode
40.80
38 / 63

Agent Level Benchmark

1 evaluations
Benchmark / mode
Score
Rank/total
Aider-Polyglot
Thinking Mode
71.40
15 / 59

Compare with other models

No curated comparisons for this model yet.

Want a custom combination? Open the compare tool

DeepSeek-R1-0528

Publisher

DeepSeek-R1-0528

Model Overview

DeepSeek-R1-0528 is an AI model published by DeepSeek-AI, released on 2025-05-28, for Reasoning model, with 671B parameters, and 64K context length, requiring about 685GB storage, under the MIT License license, with a 98.00 score on MATH-500.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code