# DeepSeek R1 Distill Qwen 14B Benchmark Scores & Performance

> DeepSeek R1 Distill Qwen 14B by DeepSeek has 5 source-displayable benchmark rows but no public overall score. It remains unranked.

Canonical page: https://benchlm.ai/models/deepseek-r1-distill-qwen-14b

Last updated: November 18, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | DeepSeek |
| Source Type | Open Weight |
| Reasoning Type | Reasoning |
| Context Window | 128K |
| Official model card | [DeepSeek-R1-Distill-Qwen-14B model card](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B) |
| Overall Score | Not computed (unranked) |
| Overall Rank | Unranked |

## Family & Coverage

- Family: DeepSeek R1 Distill
- Variant: qwen-14b
- Benchmarks covered: 5 of 818
- Sibling models: [DeepSeek R1 Distill Qwen 32B](/models/deepseek-r1-distill-qwen-32b), [DeepSeek-R1-0528-Qwen3-8B](/models/deepseek-r1-0528-qwen3-8b), [DeepSeek R1 Distill Llama 70B](/models/deepseek-r1-distill-llama-70b)
- Coverage note: Published evidence is shown below; no public overall score is assigned.

## Coding Benchmarks

| Benchmark | Score | Who ran it | Source |
|-----------|-------|------------|--------|
| [LiveCodeBench](/benchmarks/livecodebench) | 53.1% | Reported by DeepSeek | [DeepSeek: DeepSeek-R1 model card, distilled model evaluation table](https://huggingface.co/deepseek-ai/DeepSeek-R1) |
| [Codeforces](/benchmarks/codeforces) | 1481.0 | Reported by DeepSeek | [DeepSeek: DeepSeek-R1 model card, distilled model evaluation table](https://huggingface.co/deepseek-ai/DeepSeek-R1) |

## Knowledge Benchmarks

| Benchmark | Score | Who ran it | Source |
|-----------|-------|------------|--------|
| [GPQA](/benchmarks/gpqa) | 59.1% | Reported by DeepSeek | [DeepSeek: DeepSeek-R1 model card, distilled model evaluation table](https://huggingface.co/deepseek-ai/DeepSeek-R1) |

## Mathematics Benchmarks

| Benchmark | Score | Who ran it | Source |
|-----------|-------|------------|--------|
| [AIME 2024](/benchmarks/aime2024) | 69.7% | Reported by DeepSeek | [DeepSeek: DeepSeek-R1 model card, distilled model evaluation table](https://huggingface.co/deepseek-ai/DeepSeek-R1) |
| [MATH-500](/benchmarks/math-500) | 93.9% | Reported by DeepSeek | [DeepSeek: DeepSeek-R1 model card, distilled model evaluation table](https://huggingface.co/deepseek-ai/DeepSeek-R1) |

## Other DeepSeek Models

- [DeepSeek V4.1 Flash 1017](/models/deepseek-v4-1-flash) - Score: 63.94
- [DeepSeek V4 Pro](/models/deepseek-v4-pro) - Score: 62.71
- [DeepSeek V3.2](/models/deepseek-v3-2) - Score: 49.14
- [DeepSeek-R1](/models/deepseek-r1) - Score: 40.05
- [DeepSeek V3.1](/models/deepseek-v3-1) - Score: 39.57
- [DeepSeek V3 0324](/models/deepseek-v3-0324) - Score: 35.41
- [DeepSeek V3](/models/deepseek-v3) - Score: 31.06
- [DeepSeek R1 Distill Qwen 32B](/models/deepseek-r1-distill-qwen-32b) - Score: 30.39
- [DeepSeek V4 Flash 0731](/models/deepseek-v4-flash-0731) - Score: not computed
- [DeepSeek-R1-0528](/models/deepseek-r1-0528) - Score: not computed
- [DeepSeek-R1-0528-Qwen3-8B](/models/deepseek-r1-0528-qwen3-8b) - Score: not computed
- [DeepSeek R1 Distill Llama 70B](/models/deepseek-r1-distill-llama-70b) - Score: not computed
- [DeepSeek LLM 2.0](/models/deepseek-llm-2-0) - Score: not computed
- [DeepSeek-V2.5](/models/deepseek-v2-5) - Score: not computed
- [DeepSeek Coder 2.0](/models/deepseek-coder-2-0) - Score: not computed
- [DeepSeekMath V2](/models/deepseekmath-v2) - Score: not computed
