DataLearner logo
QW

QwQ-32B-Preview

Reasoning model

QwQ-32B-Preview

Release date: 2024-11-28Updated: 2024-11-28 12:53:18751
Parameters
32B
Context length
32K
Chinese support
Supported
Reasoning ability

QwQ-32B-Preview is an AI model published by Alibaba, released on 2024-11-28, for Reasoning model, with 32B parameters, and 32K context length, requiring about 64GB storage, with a 90.60 score on MATH-500.

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

QwQ-32B-Preview

Model basics

Reasoning traces
Supported
Thinking modes
Thinking modes not supported
Context length
32K tokens
Max output length
No data
Model type
Reasoning model
Modality (in / out)
No data
Release date
2024-11-28
Model file size
64GB
MoE architecture
No
Total params / Active params
32B / N/A
Knowledge cutoff
No data
QwQ-32B-Preview

Open source & experience

QwQ-32B-Preview

Official resources

Paper
DataLearnerAI blog
No blog post yet
QwQ-32B-Preview

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¥0.0060/ 1K
Batch
TypeConditionInputOutput
Text-¥0.0010/ 1K¥0.0030/ 1K
QwQ-32B-Preview

Benchmark Results

QwQ-32B-Preview currently shows benchmark results led by MMLU Pro (92 / 132, score 70.97), AIME 2024 (46 / 62, score 50), MATH-500 (35 / 44, score 90.60). 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

1 evaluations
Benchmark / mode
Score
Rank/total
70.97
92 / 132

Math and Reasoning

2 evaluations
Benchmark / mode
Score
Rank/total
90.60
35 / 44
50
46 / 62

Compare with other models

No curated comparisons for this model yet.

Want a custom combination? Open the compare tool

QwQ-32B-Preview

Publisher

QwQ-32B-Preview

Model Overview

QwQ-32B-Preview is an AI model published by Alibaba, released on 2024-11-28, for Reasoning model, with 32B parameters, and 32K context length, requiring about 64GB storage, with a 90.60 score on MATH-500.

DataLearner on WeChat

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

DataLearner WeChat QR code