DataLearner logo
QW

Qwen-72B

Foundation modelQwen

Qwen-72B

Release date: 2023-11-30Updated: 2023-11-30 16:38:30.6521,049
Parameters
72B
Context length
32K
Chinese support
Supported
Reasoning ability

Qwen-72B is an AI model published by Alibaba, released on 2023-11-30, for Foundation model, with 72B parameters, and 32K context length, requiring about 140GB storage, with a 83.30 score on C-Eval.

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

Qwen-72B

Model basics

Reasoning traces
Not supported
Thinking modes
Thinking modes not supported
Context length
32K tokens
Max output length
No data
Model type
Foundation model
Modality (in / out)
No data
Release date
2023-11-30
Model file size
140GB
MoE architecture
No
Total params / Active params
72B / N/A
Knowledge cutoff
No data
Qwen-72B

Open source & experience

Code license
Weights license
- Commercial use permitted
Live demo
No live demo
Qwen-72B

Official resources

Paper
DataLearnerAI blog
No blog post yet
Qwen-72B

API details

API speed
No data
No public API pricing yet.
Qwen-72B

Benchmark Results

Qwen-72B currently shows benchmark results led by AGIEval (2 / 28, score 62.50), C-Eval (11 / 48, score 83.30), GSM8K (25 / 70, score 78.90). 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
C-Eval
Standard Mode
83.30
11 / 48
MMLU
Standard Mode
77.40
63 / 124

Math and Reasoning

1 evaluations
Benchmark / mode
Score
Rank/total
GSM8K
Standard Mode
78.90
25 / 70

Coding and Software Engineer

2 evaluations
Benchmark / mode
Score
Rank/total
MBPP
Standard Mode
52.20
39 / 70
HumanEval
Standard Mode
35.40
70 / 101

General Evaluation

1 evaluations
Benchmark / mode
Score
Rank/total
AGIEval
Standard Mode
62.50
2 / 28

Compare with other models

No curated comparisons for this model yet.

Want a custom combination? Open the compare tool

Qwen-72B

Publisher

Qwen-72B

Model Overview

Qwen-72B is an AI model published by Alibaba, released on 2023-11-30, for Foundation model, with 72B parameters, and 32K context length, requiring about 140GB storage, with a 83.30 score on C-Eval.

DataLearner on WeChat

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

DataLearner WeChat QR code