DataLearner logo
PA

Pangu Embedded

Chat modelPangu

Pangu Embedded

Release date: 2025-06-30Updated: 2025-07-01Views: 1,061
Parameters
7B
Context length
32K
Multilingual
Supported
Reasoning ability
3/5

Pangu Embedded is an AI model published by Huawei, released on 2025-06-30, for Chat model, with 7B parameters, and 32K context length, requiring about 14GB storage, with a 95.98 score on GSM8K.

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

Pangu Embedded

Model basics

Reasoning traces
No data
Thinking modes
Thinking modes not supported
Context length
32K tokens
Max output length
32K tokens
Model type
Chat model
Modality (in / out)
Text → Text
Release date
2025-06-30
Model file size
14GB
MoE architecture
No
Total params / Active params
7B / Not applicable
Knowledge cutoff
No data
Pangu Embedded

Open source & experience

Code license
Weights license
- Commercial use permitted
Live demo
N/A
Pangu Embedded

Official resources

Paper
DataLearnerAI blog
Pangu Embedded

API details

API speed
3/5
No public API pricing yet.
Pangu Embedded

Benchmark Results

Pangu Embedded currently shows benchmark results led by GSM8K (4 / 70, score 95.98), GPQA (5 / 16, score 68), AIME 2024 (24 / 62, score 81.90). 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

2 evaluations
Benchmark / mode
Score
Rank/total
MMLU Pro
Standard Mode
79
67 / 133
GPQA
Standard Mode
68
5 / 16

Math and Reasoning

3 evaluations
Benchmark / mode
Score
Rank/total
GSM8K
Standard Mode
95.98
4 / 70
MATH-500
Standard Mode
92.40
31 / 44
AIME 2024
Standard Mode
81.90
24 / 62

Coding and Software Engineer

1 evaluations
Benchmark / mode
Score
Rank/total
LiveCodeBench
Standard Mode
67.10
60 / 127
Pangu Embedded

Publisher

Pangu Embedded

Model Overview

Pangu Embedded is an AI model published by Huawei, released on 2025-06-30, for Chat model, with 7B parameters, and 32K context length, requiring about 14GB storage, with a 95.98 score on GSM8K.

DataLearner on WeChat

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

DataLearner WeChat QR code