How much does R1 Distill Qwen 32B cost?

R1 Distill Qwen 32B costs $0.29 per million input tokens and $0.29 per million output tokens. For a typical conversation (~2,000 tokens), that's approximately $0.001 per message.

What benchmarks has R1 Distill Qwen 32B been tested on?

R1 Distill Qwen 32B has been evaluated on 6 benchmarks. Top scores: IFEval: 41.9, MMLU-PRO: 41.0, BBH (HuggingFace): 17.1.

Is R1 Distill Qwen 32B open source?

Yes, R1 Distill Qwen 32B is open source.

How does R1 Distill Qwen 32B compare to Claude 2?

R1 Distill Qwen 32B has an average score of 42.2 while Claude 2 scores 41.8. R1 Distill Qwen 32B outperforms Claude 2 overall. See full comparison →

Home/Models/R1 Distill Qwen 32B

R1 Distill Qwen 32B

Name: R1 Distill Qwen 32B
Price: 0.29 USD
Author: DeepSeek

by DeepSeek · Released Jan 2025

Open Source

42.2

avg score

Rank #136

Compare

Better than 42% of all models

Context

33K tokens (~16 books)

Input $/1M

$0.29

Output $/1M

$0.29

Type

text

License

Open Source

Benchmarks

6 tested

Data updated today

About

DeepSeek R1 Distill Qwen 32B is a distilled large language model based on [Qwen 2.5 32B](https://huggingface.co/Qwen/Qwen2.5-32B), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). It outperforms OpenAI's o1-mini across various benchmarks, achieving new...

Tested on 6 benchmarks with 23.0% average. Top scores: IFEval (41.9%), MMLU-PRO (41.0%), BBH (HuggingFace) (17.1%).

Looking for similar performance at lower cost?
Llama 3 8B Instruct scores 41.7 (99% as good) at $0.03/1M input · 90% cheaper

Capabilities

reasoning

16.1

#108 globally

math

17.1

#176 globally

knowledge

22.8

#189 globally

language

41.9

#112 globally

general

17.1

#45 globally

Benchmark Scores

Compare All

Tested on 6 benchmarks · Ranked across 5 categories

Score Distribution (all 233 models)

0255075100

▲ You are here

reasoningCompare reasoning →

MUSR

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

16.1—

mathCompare math →

MATH Level 5

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

17.1—

knowledgeCompare knowledge →

MMLU-PRO

HuggingFace MMLU-Pro. Harder version of MMLU with 10 answer choices instead of 4 and more challenging questions.

41.0—

GPQA

HuggingFace evaluation of GPQA (Graduate-Level Google-Proof Q&A). PhD-level science questions that cannot be easily searched.

4.6—

Quick compare:

vs Claude 2

vs Llama 3 8B Instruct

vs Yi 6B

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

Similar Models

Frequently Asked Questions

R1 Distill Qwen 32B is an open-source text AI model by DeepSeek, released in January 2025. It has an average benchmark score of 42.2. Context window: 33K tokens.

Benchmarks

IFEval MMLU-PRO BBH (HuggingFace)MATH Level 5 MUSR

DeepSeek · Provider DeepSeek · Economy All Models Compare Models Pricing Developers · API

R1 Distill Qwen 32B

Frequently Asked Questions

Related Models

Benchmarks

Related Pages