How much does QwQ 32B cost?

QwQ 32B costs $0.15 per million input tokens and $0.58 per million output tokens. For a typical conversation (~2,000 tokens), that's approximately $0.001 per message.

What benchmarks has QwQ 32B been tested on?

QwQ 32B has been evaluated on 13 benchmarks. Top scores: Chatbot Arena Elo — Overall: 1335.8, Fiction.LiveBench: 83.3, Lech Mazur Writing: 80.2.

How does QwQ 32B compare to Qwen3 30B A3B?

QwQ 32B has an average score of 33.7 while Qwen3 30B A3B scores 34.0. Qwen3 30B A3B slightly outperforms QwQ 32B overall. QwQ 32B costs $0.15/1M input vs Qwen3 30B A3B at $0.12/1M input. See full comparison →

Home/Models/QwQ 32B

QwQ 32B

Name: QwQ 32B · benchmarks, pricing and providers
Creator: BenchGecko

by Alibaba Qwen · Released Mar 2025

Open Source

33.7

avg score

Rank #230

Compare

Better than 26% of all models

Context

131K tokens (~66 books)

Input $/1M

$0.15

Output $/1M

$0.58

Type

text

License

Open Source

Benchmarks

13 tested

Data as of 2026-04-28

About

QwQ is the reasoning model of the Qwen series. Compared with conventional instruction-tuned models, QwQ, which is capable of thinking and reasoning, can achieve significantly enhanced performance in downstream tasks,...

Tested on 13 benchmarks · BenchGecko score 33.7. Top scores: Chatbot Arena Elo — Overall (1335.8%), Fiction.LiveBench (83.3%), Lech Mazur Writing (80.2%).

Looking for similar performance at lower cost?
Qwen3 30B A3B scores 34.0 (101% as good) at $0.12/1M input · 20% cheaper

Capabilities

coding

20.9

#176 globally

reasoning

11.1

#172 globally

math

37.6

#163 globally

knowledge

36.8

#215 globally

general

2.9

#215 globally

language

39.8

#133 globally

Benchmark Scores

Compare All

Tested on 13 benchmarks · Ranked across 7 categories

Score Distribution (all 312 models)

0255075100

▲ You are here

codingCompare coding →

Aider polyglot

Multi-language code editing from Aider. Tests editing ability across Python, JavaScript, TypeScript, Java, C++, Go, Rust, and more.

20.9·

reasoningCompare reasoning →

MUSR

HuggingFace MuSR (Multi-Step Reasoning). Tests multi-hop reasoning requiring chaining multiple facts together.

11.1·

mathCompare math →

OTIS Mock AIME 2024-2025

Mock AIME (American Invitational Mathematics Exam) problems from OTIS. Tests mathematical competition performance.

59.1·

MATH Level 5

HuggingFace evaluation of MATH Level 5 problems. Competition math requiring advanced reasoning and proof construction.

16.1·

Quick compare:

vs Qwen3 30B A3B

vs GPT-4o-mini (2024-07-18)

vs LLaMA-13B

Excellent (85+) Good (70-85) Average (50-70) Below (<50)

Similar Models

Qwen3 30B A3B

Alibaba Qwen

34.0$0.12/1M

GPT-4o-mini (2024-07-18)

OpenAI

33.4$0.15/1M

LLaMA-13B

Frequently Asked Questions

QwQ 32B is an open-source text AI model by Alibaba Qwen, released in March 2025. It has an average benchmark score of 33.7. Context window: 131K tokens.

Benchmarks

Chatbot Arena Elo — Overall Fiction.LiveBench Lech Mazur Writing OTIS Mock AIME 2024-2025 GPQA diamond

Alibaba Qwen · Provider Alibaba Qwen · Economy All Models Compare Models Pricing Developers · API Context Window · Glossary

Key facts · as of 2026-04-28

QwQ 32B by Alibaba Qwen. BenchGecko score 33.7, rank 230 of 312 scored models (normalized average of public benchmark scores).
List price $0.15 input · $0.58 output per 1M tokens (as of 2026-04-28).

How to cite · data as of 2026-04-28

QwQ 32B · benchmarks, pricing and providers. BenchGecko, data as of 2026-04-28. https://benchgecko.ai/model/qwq-32b

Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP

QwQ 32B

Frequently Asked Questions

Related Models

Benchmarks

Related Pages

Key facts · as of 2026-04-28

How to cite · data as of 2026-04-28