DeepSeek R1 Distill Qwen 7B
Zero-eval
by DeepSeek
About
DeepSeek R1 Distill Qwen 7B is a language model developed by DeepSeek. It achieves strong performance with an average score of 65.7% across 4 benchmarks. It excels particularly in MATH-500 (92.8%), AIME 2024 (83.3%), GPQA (49.1%). It's licensed for commercial use, making it suitable for enterprise applications. Released in 2025, it represents DeepSeek's latest advancement in AI technology.
Timeline
AnnouncedJan 20, 2025
ReleasedJan 20, 2025
Specifications
Training Tokens14.8T
License & Family
License
MIT
Benchmark Performance Overview
Performance metrics and category breakdown
Overall Performance
4 benchmarks
Average Score
65.7%
Best Score
92.8%
High Performers (80%+)
2Top Categories
math
92.8%
general
66.2%
code
37.6%
Benchmark Performance
Top benchmark scores with normalized values (0-100%)
Ranking Across Benchmarks
Position relative to other models on each benchmark
MATH-500
Rank #14 of 22
#11DeepSeek R1 Distill Qwen 14B
93.9%
#12DeepSeek-V3 0324
94.0%
#13DeepSeek R1 Distill Qwen 32B
94.3%
#14DeepSeek R1 Distill Qwen 7B
92.8%
#15QwQ-32B
90.6%
#16QwQ-32B-Preview
90.6%
#17DeepSeek-V3
90.2%
AIME 2024
Rank #13 of 41
#10Qwen3 235B A22B
85.7%
#11o1-pro
86.0%
#12DeepSeek R1 Zero
86.7%
#13DeepSeek R1 Distill Qwen 7B
83.3%
#14DeepSeek R1 Distill Qwen 32B
83.3%
#15Qwen3 32B
81.4%
#16Phi 4 Reasoning Plus
81.3%
GPQA
Rank #66 of 115
#63Qwen2.5 32B Instruct
49.5%
#64GPT-4.1 nano
50.3%
#65Claude 3 Opus
50.4%
#66DeepSeek R1 Distill Qwen 7B
49.1%
#67Qwen2.5 72B Instruct
49.0%
#68DeepSeek R1 Distill Llama 8B
49.0%
#69Kimi K2 Base
48.1%
LiveCodeBench
Rank #27 of 44
#24DeepSeek-V3
37.6%
#25DeepSeek R1 Distill Llama 8B
39.6%
#26Llama 4 Maverick
43.4%
#27DeepSeek R1 Distill Qwen 7B
37.6%
#28Gemini 2.0 Flash
35.1%
#29Gemini 2.5 Flash-Lite
33.7%
#30Llama 4 Scout
32.8%
All Benchmark Results for DeepSeek R1 Distill Qwen 7B
Complete list of benchmark scores with detailed information
MATH-500 MATH-500 benchmark | math | text | 0.93 | 92.8% | Self-reported |
AIME 2024 AIME 2024 benchmark | general | text | 0.83 | 83.3% | Self-reported |
GPQA GPQA benchmark | general | text | 0.49 | 49.1% | Self-reported |
LiveCodeBench LiveCodeBench benchmark | code | text | 0.38 | 37.6% | Self-reported |