NEWHow AI models draw the world map · Gecko Tests
Beta
Home/Models/DeepSeek R1 Distill Qwen 1.5B
DeepSeek logo

DeepSeek R1 Distill Qwen 1.5B

by DeepSeek · Released Jan 2025

Open Source
13.4
avg score
Rank #294
Compare
Better than 6% of all models
Context
N/A
Input $/1M
n/a
Output $/1M
n/a
Type
text-generation
License
Open Source
Benchmarks
6 tested
Data as of
About

Deepseek-ai text generation model. 630K downloads on HuggingFace.

Tested on 6 benchmarks · BenchGecko score 13.4. Top scores: IFEval (34.6%), MATH Level 5 (16.9%), BBH (HuggingFace) (4.7%).

Capabilities
reasoning
3.0
#217 globally
math
16.9
#244 globally
knowledge
1.4
#303 globally
general
4.7
#207 globally
language
34.6
#138 globally
Benchmark Scores
Compare All
Tested on 6 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.

3.0·
mathCompare math →
MATH Level 5

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

16.9·
knowledgeCompare knowledge →
MMLU-PRO

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

2.1·
GPQA

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

0.8·
Quick compare:Alibaba logovs Qwen2.5 0.5B InstructMeta logovs Llama 3.2 3B Instruct (free)OpenAI logovs Gpt2
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
Alibaba logo
Qwen2.5 0.5B Instruct
Alibaba
13.3n/a
Meta logo
Llama 3.2 3B Instruct (free)
Meta
14.2Free
OpenAI logo
Gpt2
OpenAI
11.8n/a
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-15b
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
Alibaba logoQwen2.5 0.5B Instruct
13.3
Meta logoLlama 3.2 3B Instruct (free)
14.2
OpenAI logoGpt2
11.8
Meta logoLlama 3.2 1B Instruct
11.7
DeepSeek R1 Distill Qwen 1.5B is an open-source text-generation AI model by DeepSeek, released in January 2025. It has an average benchmark score of 13.4.

Related Models

Qwen2.5 0.5B Instruct · AlibabaLlama 3.2 3B Instruct (free) · MetaGpt2 · OpenAILlama 3.2 1B Instruct · MetaQwen-1_8B · Alibaba Qwen

Benchmarks

IFEvalMATH Level 5BBH (HuggingFace)MUSRMMLU-PRO

Related Pages

DeepSeek · ProviderDeepSeek · EconomyAll ModelsCompare ModelsPricingDevelopers · API

Key facts · as of 2026-04-09

  • DeepSeek R1 Distill Qwen 1.5B by DeepSeek. BenchGecko score 13.4, rank 294 of 312 scored models (normalized average of public benchmark scores).
  • List price n/a input · n/a output per 1M tokens (as of 2026-04-09).

How to cite · data as of 2026-04-09

DeepSeek R1 Distill Qwen 1.5B · benchmarks, pricing and providers. BenchGecko, data as of 2026-04-09. https://benchgecko.ai/model/deepseek-ai-deepseek-r1-distill-qwen-15b

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