Top 4% of all models
Context
N/A
Input $/1M
TBD
Output $/1M
TBD
Type
text-generation
License
Open Source
Benchmarks
11 tested
Data updated today
About
Deepseek-ai text generation model. 573K downloads on HuggingFace.
Tested on 11 benchmarks with 56.0% average. Top scores: JCommonsenseQA (93.7%), JSQuAD (89.8%), JNLI (82.4%).
Capabilities
reasoning
28.7
#86 globally
math
57.0
#55 globally
knowledge
29.5
#174 globally
language
71.7
#66 globally
general
40.7
#18 globally
Benchmark Scores
Compare AllTested on 11 benchmarks · Ranked across 5 categories
Score Distribution (all 231 models)
0255075100
▲ You are here
reasoningCompare reasoning →
MUSR
28.7—HuggingFace MuSR (Multi-Step Reasoning). Tests multi-hop reasoning requiring chaining multiple facts together.
mathCompare math →
MATH Level 5
57.0—HuggingFace evaluation of MATH Level 5 problems. Competition math requiring advanced reasoning and proof construction.
knowledgeCompare knowledge →
MMLU-PRO
40.7—HuggingFace MMLU-Pro. Harder version of MMLU with 10 answer choices instead of 4 and more challenging questions.
GPQA
18.3—HuggingFace evaluation of GPQA (Graduate-Level Google-Proof Q&A). PhD-level science questions that cannot be easily searched.
vs Qwen3.6 Plus
vs GPT-5 Chat Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Links
Info
Research
Documentation
Community
Source Code
BenchGecko API
deepseek-ai-deepseek-r1-distill-qwen-14b
Specifications
- Typetext-generation
- ContextN/A
- ReleasedJan 2025
- LicenseOpen Source
- StatusActive
Available On
DeepSeekTBDLearn More
Share & Export
Frequently Asked Questions
DeepSeek R1 Distill Qwen 14B is an open-source text-generation AI model by DeepSeek, released in January 2025. It has an average benchmark score of 88.3.