DataLearner logo
QW

Qwen3-32B

Reasoning modelQwen3

Qwen3-32B

Release date: 2025-04-28Updated: 2026-07-17Views: 3,229
Live demoGitHubHugging FaceCompare
Parameters
32B
Context length
128K
Multilingual
Supported
Reasoning ability
3/5

Qwen3-32B is a reasoning model from Alibaba, released on 2025-04-28. It accepts text input and returns text output. The cataloged parameter count is 32B. The recorded context window is 128K, and the recorded maximum output is 16K. Cataloged capabilities include Reasoning model and Multilingual. The checkpoint is listed under the Apache 2.0 license, with the license link included in the model references. Use the linked references to confirm current access, licensing, and provider-specific limits.

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

Qwen3-32B

Model basics

Reasoning traces
Supported
Thinking modes
Thinking modes not supported
Context length
128K tokens
Max output length
16K tokens
Model type
Reasoning model
Modality (in / out)
Text → Text
Release date
2025-04-28
Model file size
64GB
MoE architecture
No
Total params / Active params
32B / Not applicable
Knowledge cutoff
No data
Qwen3-32B

Open source & experience

Code license
Apache 2.0
Weights license
Apache 2.0- Commercial use permitted
GitHub repo
N/A
Hugging Face
huggingface.co/Qwen/Qwen3-32B
Live demo
chat.qwen.ai
Qwen3-32B

Official resources

Paper
Paper
DataLearnerAI blog
DataLearnerAI blog
Qwen3-32B

API details

API speed
4/5
💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.
Learn about pricing modes
Standard
TypeConditionInputOutput
Text-¥0.0012/ 1K¥0.0048/ 1K

“—” means the modality is not billed in that direction, or the vendor has not published a price for it.

Qwen3-32B

Benchmark Results

Qwen3-32B currently shows benchmark results led by C-Eval (9 / 48, score 87.30), MATH-500 (14 / 44, score 97.20), AIME 2024 (25 / 62, score 81.40). 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

3 evaluations
Benchmark / mode
Score
Rank/total
C-Eval
Standard Mode
83.30
11 / 48
C-Eval
Thinking Mode
87.30
9 / 48
LiveBench
Thinking Mode
43.56
105 / 115

General Evaluation

2 evaluations
Benchmark / mode
Score
Rank/total
GPQA Diamond
Standard Mode
54.60
236 / 270
GPQA Diamond
Thinking Mode
68.40
201 / 270

Math and Reasoning

6 evaluations
Benchmark / mode
Score
Rank/total
MATH-500
Standard Mode
88.60
38 / 44
MATH-500
Thinking Mode
97.20
14 / 44
AIME 2024
Standard Mode
31
55 / 62
AIME 2024
Thinking Mode
81.40
25 / 62
AIME2025
Standard Mode
20.20
105 / 106
AIME2025
Thinking Mode
72.90
69 / 106

Coding and Software Engineer

4 evaluations
Benchmark / mode
Score
Rank/total
CodeForces
Standard Mode
1353
18 / 20
CodeForces
Thinking Mode
1977
15 / 20
LiveCodeBench
Standard Mode
31.30
121 / 127
LiveCodeBench
Thinking Mode
65.70
65 / 127

Agent Level Benchmark

1 evaluations
Benchmark / mode
Score
Rank/total
Aider-Polyglot
Standard Mode
40
39 / 59
View benchmark analysisCompare with other models
Qwen3-32B

Publisher

Qwen3-32B

Model Overview

Qwen3-32B is a reasoning model from Alibaba, released on 2025-04-28.

It accepts text input and produces text output. Its cataloged capabilities include Reasoning model and Multilingual. The cataloged parameter count is 32B. The recorded context window is 128K, and the recorded maximum output is 16K.

The checkpoint is listed under the Apache 2.0 license, with the license link included in the model references. The page records 2 API pricing rules from the listed provider; current provider pricing and conditions should be checked before deployment. The evaluation section contains 18 cataloged benchmark results with their recorded modes and scores. The page links 4 release, model-card, repository, or provider references for checking the underlying claims. Specifications, availability, and prices can change; undisclosed values are intentionally left unstated.

Qwen3-32B

FAQ

What is Qwen3-32B?

Qwen3-32B is a reasoning model from Alibaba, released on 2025-04-28. It accepts text input and returns text output. The cataloged parameter count is 32B. The recorded context window is 128K, and the recorded maximum output is 16K. Cataloged capabilities include Reasoning model and Multilingual. The checkpoint is listed under the Apache 2.0 license, with the license link included in the model references. Use the linked references to confirm current access, licensing, and provider-specific limits.

What input and output modalities does Qwen3-32B support?

The current model record lists text as input and text as output.

What are the main recorded specifications for Qwen3-32B?

The cataloged parameter count is 32B. The recorded context window is 128K, and the recorded maximum output is 16K. Fields without a source-backed value remain undisclosed.

Does Qwen3-32B have API pricing?

The page records 2 API pricing rules from the listed provider; current provider pricing and conditions should be checked before deployment.

Are benchmark results available for Qwen3-32B?

The evaluation section contains 18 cataloged benchmark results with their recorded modes and scores. Compare only results that use the same benchmark version and evaluation mode.

Is Qwen3-32B open source?

The checkpoint is listed under the Apache 2.0 license, with the license link included in the model references. Review the linked license text before commercial or derivative use.

DataLearner on WeChat

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

DataLearner WeChat QR code