DataLearner logo
DE

DeepSeek-R1-0528-Qwen3-8B

Reasoning modelDeepSeek R1 DistillDeepSeek R1 Distill

DeepSeek-R1-0528-Qwen3-8B

Release date: 2025-05-30Updated: 2025-05-30Views: 1,471
Live demoGitHubHugging FaceCompare
Parameters
8B
Context length
64K
Multilingual
Supported
Reasoning ability
3/5

DeepSeek-R1-0528-Qwen3-8B is an AI model published by DeepSeek-AI, released on 2025-05-30, for Reasoning model, with 8B parameters, and 64K context length, requiring about 16GB storage, with a 63.70 score on AIME2025.

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-Qwen3-8B

Model basics

Reasoning traces
Supported
Thinking modes
Thinking modes not supported
Context length
64K tokens
Max output length
40K tokens
Model type
Reasoning model
Modality (in / out)
Text → Text
Release date
2025-05-30
Model file size
16GB
MoE architecture
No
Total params / Active params
8B / Not applicable
Knowledge cutoff
No data
DeepSeek-R1-0528-Qwen3-8B

Open source & experience

Code license
Weights license
MIT License- Commercial use permitted
GitHub repo
N/A
Live demo
N/A
DeepSeek-R1-0528-Qwen3-8B

Official resources

Paper
N/A
DataLearnerAI blog
N/A
DeepSeek-R1-0528-Qwen3-8B

API details

API speed
4/5
No public API pricing yet.
DeepSeek-R1-0528-Qwen3-8B

Benchmark Results

DeepSeek-R1-0528-Qwen3-8B currently shows benchmark results led by AIME2025 (129 / 215, score 63.70), LiveCodeBench (163 / 250, score 51.30), GPQA Diamond (372 / 462, score 61.20). 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
Tool usage

General Knowledge

1 evaluations
Benchmark / mode
Score
Rank/total
HLE
Thinking Mode
5.90
462 / 563

General Evaluation

1 evaluations
Benchmark / mode
Score
Rank/total
GPQA Diamond
Thinking Mode
61.20
372 / 462

Coding and Software Engineer

1 evaluations
Benchmark / mode
Score
Rank/total
LiveCodeBench
Thinking Mode
51.30
163 / 250

Math and Reasoning

1 evaluations
Benchmark / mode
Score
Rank/total
AIME2025
Thinking Mode
63.70
129 / 215

Instruction Following

1 evaluations
Benchmark / mode
Score
Rank/total
IF Bench
Thinking Mode
19.90
280 / 282

Agent Level Benchmark

1 evaluations
Benchmark / mode
Score
Rank/total
Terminal Bench Hard
Thinking ModeTools
1.50
237 / 244
DeepSeek-R1-0528-Qwen3-8B

Publisher

DeepSeek-R1-0528-Qwen3-8B

Model Overview

DeepSeek-R1-0528-Qwen3-8B is an AI model published by DeepSeek-AI, released on 2025-05-30, for Reasoning model, with 8B parameters, and 64K context length, requiring about 16GB storage, with a 63.70 score on AIME2025.

DataLearner on WeChat

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

DataLearner WeChat QR code