DataLearner logo
QW

QwQ-32B

Reasoning model

QwQ-32B

Release date: 2025-03-06Updated: 2025-03-06Views: 1,414
Parameters
32.5B
Context length
128K
Multilingual
Supported
Reasoning ability
No data

QwQ-32B is an AI model published by Alibaba, released on 2025-03-06, for Reasoning model, with 32.5B parameters, and 128K context length, requiring about 64GB storage, with a 1255.10 score on Creative Writing.

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

QwQ-32B

Model basics

Reasoning traces
Supported
Thinking modes
Thinking modes not supported
Context length
128K tokens
Max output length
No data
Model type
Reasoning model
Modality (in / out)
Text → Text
Release date
2025-03-06
Model file size
64GB
MoE architecture
No
Total params / Active params
32.5B / Not applicable
Knowledge cutoff
No data
QwQ-32B

Open source & experience

Code license
Weights license
Apache 2.0- Commercial use permitted
GitHub repo
N/A
QwQ-32B

Official resources

Paper
DataLearnerAI blog
QwQ-32B

API details

API speed
No data
💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.
Standard
TypeConditionInputOutput
Text-¥0.0020/ 1K tokens¥0.0060/ 1K tokens

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

QwQ-32B

Benchmark Results

QwQ-32B currently shows benchmark results led by AIME 2024 (29 / 62, score 79.50), MMLU Pro (84 / 176, score 76), LiveCodeBench (122 / 250, score 63.10). 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
MMLU Pro
Standard Mode
76
84 / 176
MMLU Pro
unknown
69.07
103 / 176
HLE
Thinking Mode
7.30
435 / 563

Coding and Software Engineer

2 evaluations
Benchmark / mode
Score
Rank/total
LiveCodeBench
Thinking Mode
63.10
122 / 250
HumanEval
Standard Mode
19
133 / 140

General Evaluation

2 evaluations
Benchmark / mode
Score
Rank/total
GPQA Diamond
Standard Mode
58
387 / 462
GPQA Diamond
Thinking Mode
59.30
382 / 462

Math and Reasoning

3 evaluations
Benchmark / mode
Score
Rank/total
MATH-500
Standard Mode
91
34 / 45
AIME 2024
Standard Mode
79.50
29 / 62
AIME2025
Thinking Mode
29
185 / 215

Writing and Creative Capabilities

1 evaluations
Benchmark / mode
Score
Rank/total
Creative Writing
Standard Mode
1255.10
78 / 106

Agent Level Benchmark

1 evaluations
Benchmark / mode
Score
Rank/total
Aider-Polyglot
Thinking Mode
20.90
49 / 59

Instruction Following

1 evaluations
Benchmark / mode
Score
Rank/total
IF Bench
Thinking Mode
38.80
225 / 282
QwQ-32B

Publisher

QwQ-32B

Model Overview

QwQ-32B is an AI model published by Alibaba, released on 2025-03-06, for Reasoning model, with 32.5B parameters, and 128K context length, requiring about 64GB storage, with a 1255.10 score on Creative Writing.

DataLearner on WeChat

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

DataLearner WeChat QR code