NEWHow AI models draw the world map · Gecko Tests
Beta
Home/Models/DeepSeek R1 Distill Qwen 32B
DeepSeek logo

DeepSeek R1 Distill Qwen 32B

by DeepSeek · Released Jan 2025

Open Source
58.8
avg score
Rank #93
Compare
Better than 70% of all models
Context
N/A
Input $/1M
n/a
Output $/1M
n/a
Type
text-generation
License
Open Source
Benchmarks
15 tested
Data as of
About

Deepseek-ai text generation model. 958K downloads on HuggingFace.

Tested on 15 benchmarks · BenchGecko score 58.8. Top scores: JCommonsenseQA (95.3%), JSQuAD (89.2%), JNLI (85.6%).

Capabilities
reasoning
16.1
#149 globally
math
36.3
#169 globally
knowledge
23.4
#252 globally
general
17.1
#174 globally
language
73.9
#70 globally
Benchmark Scores
Compare All
Tested on 15 benchmarks · Ranked across 5 categories
Score Distribution (all 312 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 →
OTIS Mock AIME 2024-2025

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

55.5·
MATH Level 5

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

17.1·
knowledgeCompare knowledge →
GPQA diamond

Graduate-level science questions written by PhD experts. Diamond subset contains questions where experts disagree, testing deep understanding.

52.2·
MMLU-PRO

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

41.0·
Balrog

Broad Assessment of Language and Reasoning Over Games. Tests strategic and logical reasoning through game scenarios.

19.5·
Quick compare:Google DeepMind logovs Gemini 2.5 ProxAI logovs Grok 4DeepSeek logovs DeepSeek V4.1 Flash
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Model Family · DeepSeek DeepSeek R1
Jan 2025
53.1
n/an/actx11 benchmarks
Jan 2025
13.4-39.7
n/an/actx6 benchmarks
Jan 2025
73.7+60.3
n/an/actx15 benchmarks
Jan 2025
58.8-14.9
n/an/actx15 benchmarks
Jan 2025
36.6-22.2
n/an/actx11 benchmarks
See the full DeepSeek R1 family →
Similar Models
Google DeepMind logo
Gemini 2.5 Pro
Google DeepMind
58.7$1.25/1M
xAI logo
Grok 4
xAI
58.7n/a
DeepSeek logo
DeepSeek V4.1 Flash
DeepSeek
58.7$0.15/1M
Links
Info
DeepSeekPricing explorerDevelopers · API
Research
Technical Report
Documentation
API DocsPlayground
Community
@DeepSeek
Source Code
GitHubHugging Face
BenchGecko API
deepseek-ai-deepseek-r1-distill-qwen-32b
Specifications
  • Typetext-generation
  • ContextN/A
  • ReleasedJan 2025
  • LicenseOpen Source
  • StatusActive
Available On
DeepSeek logoDeepSeekn/a
Categories
reasoningmathknowledgegenerallanguage
Learn More
transformeropen weightstokens
Share & Export
Tweet
Related Models
Google DeepMind logoGemini 2.5 Pro
58.7
xAI logoGrok 4
58.7
DeepSeek logoDeepSeek V4.1 Flash
58.7
Nemotron-4 15B
58.9
DeepSeek R1 Distill Qwen 32B is an open-source text-generation AI model by DeepSeek, released in January 2025. It has an average benchmark score of 58.8.

Related Models

Gemini 2.5 Pro · Google DeepMindGrok 4 · xAIDeepSeek V4.1 Flash · DeepSeekNemotron-4 15B · UnknownClaude Opus 4.5 · Anthropic

Benchmarks

JCommonsenseQAJSQuADJNLIJMMLULLM-JP — Overall

Related Pages

DeepSeek · ProviderDeepSeek · EconomyAll ModelsCompare ModelsPricingDevelopers · API

Key facts · as of 2026-06-22

  • DeepSeek R1 Distill Qwen 32B by DeepSeek. BenchGecko score 58.8, rank 93 of 312 scored models (normalized average of public benchmark scores).
  • List price n/a input · n/a output per 1M tokens (as of 2026-06-22).

How to cite · data as of 2026-06-22

DeepSeek R1 Distill Qwen 32B · benchmarks, pricing and providers. BenchGecko, data as of 2026-06-22. https://benchgecko.ai/model/deepseek-ai-deepseek-r1-distill-qwen-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