DeepSeek, open weights

# DeepSeek-R1-Distill-Llama-70B

> DeepSeek-R1-Distill-Llama-70B by DeepSeek, released January 2025. Ranked #195 of 354 with a Noometry Index of 37.8. Scores, sources and comparisons.
- Canonical page: https://noometry.com/models/deepseek-r1-distill-llama-70b
- Last updated: 2026-10-10
- Title: DeepSeek-R1-Distill-Llama-70B Benchmarks, Price & Rank (October 2026)

DeepSeek-R1-Distill-Llama-70B by DeepSeek ranks 195th of 354 ranked models on the Noometry Index as of October 2026, with a score of 37.8. Its strongest category is reasoning, where it ranks 156th.

Last verified October 10, 2026

## Specifications

- **Noometry rank:** #195 of 354
- **Index score:** 37.8
- **Evidence:** Confirmed 13 results
- **Provider:** [![](/logos/deepseek.svg) DeepSeek](https://noometry.com/providers/deepseek)
- **Released:** January 20, 2025
- **Weights:** Open weights
- **Reasoning:** Unknown
- **Context window:** —
- **Max output:** —
- **Input price:** Not listed
- **Output price:** Not listed
- **Blended price:** Not listed
- **Output speed:** 18 tokens/s [Kagi](https://help.kagi.com/kagi/ai/llm-benchmark.html)
- **Value:** Not ranked
- **Knowledge cutoff:** Unknown

## Category scores

Each category score combines every public result we have in that category.

DeepSeek-R1-Distill-Llama-70B category scores

1.  Coding 36.8
2.  Reasoning 24.9
3.  Math 36.0
4.  Knowledge 30.7
5.  Instruction Following 68.2
6.  Writing & Preference 49.0
7.  020406080

DeepSeek-R1-Distill-Llama-70B category ranks
| Category | Score | Rank | Results |
| --- | --- | --- | --- |
| [Coding](https://noometry.com/best/coding) | 36.8 | #202 | 3 |
| [Reasoning](https://noometry.com/best/reasoning) | 24.9 | #156 | 3 |
| [Math](https://noometry.com/best/math) | 36.0 | #176 | 3 |
| [Knowledge](https://noometry.com/best/knowledge) | 30.7 | #225 | 1 |
| [Instruction Following](https://noometry.com/best/instruction-following) | 68.2 | #190 | 1 |
| [Writing & Preference](https://noometry.com/best/writing) | 49.0 | #194 | 1 |

## Strengths and weaknesses

Categories where DeepSeek-R1-Distill-Llama-70B places highest and lowest among the models ranked in each, with its score against that category's median.

### Strongest categories

DeepSeek-R1-Distill-Llama-70B: strongest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Reasoning](https://noometry.com/best/reasoning) | 24.9 | +1.3 | #156 of 350, top 45% |
| [Math](https://noometry.com/best/math) | 36.0 | −0.6 | #176 of 327, top 54% |
| [Coding](https://noometry.com/best/coding) | 36.8 | −1.9 | #202 of 340, top 60% |

### Weakest categories

DeepSeek-R1-Distill-Llama-70B: weakest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Knowledge](https://noometry.com/best/knowledge) | 30.7 | −6.7 | #225 of 314, top 72% |
| [Instruction Following](https://noometry.com/best/instruction-following) | 68.2 | −3.1 | #190 of 305, top 63% |
| [Writing & Preference](https://noometry.com/best/writing) | 49.0 | −4.8 | #194 of 312, top 63% |

## Closest competitors

The models ranked just above and below DeepSeek-R1-Distill-Llama-70B. When scores are this close, price and speed are often the better way to choose.

Models ranked closest to DeepSeek-R1-Distill-Llama-70B
| Model | Rank | Score | Blended $/M | Speed |  |
| --- | --- | --- | --- | --- | --- |
| [Olmo 3.1 32b Think](https://noometry.com/models/olmo-3-1-32b-think) | #191 | 37.9 | — | — | [Compare](https://noometry.com/compare/deepseek-r1-distill-llama-70b-vs-olmo-3-1-32b-think) |
| [GPT-5-Codex](https://noometry.com/models/gpt-5-codex) | #192 | 37.9 | $3.44 | 95 | [Compare](https://noometry.com/compare/deepseek-r1-distill-llama-70b-vs-gpt-5-codex) |
| [Hunyuan Standard 2025 02 10](https://noometry.com/models/hunyuan-standard) | #193 | 37.9 | — | — | [Compare](https://noometry.com/compare/deepseek-r1-distill-llama-70b-vs-hunyuan-standard) |
| [Gemini 2.0 Flash-Lite](https://noometry.com/models/gemini-2-0-flash-lite) | #194 | 37.8 | — | — | [Compare](https://noometry.com/compare/deepseek-r1-distill-llama-70b-vs-gemini-2-0-flash-lite) |
| [MiniMax-M2.7](https://noometry.com/models/minimax-m2-7) | #196 | 37.7 | $0.52 | — | [Compare](https://noometry.com/compare/deepseek-r1-distill-llama-70b-vs-minimax-m2-7) |
| [Gemini Advanced 0514](https://noometry.com/models/gemini-advanced) | #197 | 37.7 | — | — | [Compare](https://noometry.com/compare/deepseek-r1-distill-llama-70b-vs-gemini-advanced) |
| [Grok 2 Mini 2024 08 13](https://noometry.com/models/grok-2-mini) | #198 | 37.7 | — | — | [Compare](https://noometry.com/compare/deepseek-r1-distill-llama-70b-vs-grok-2-mini) |
| [Mercury](https://noometry.com/models/mercury) | #199 | 37.6 | — | 35 | [Compare](https://noometry.com/compare/deepseek-r1-distill-llama-70b-vs-mercury) |

Sponsored placements are available on pages like this one. [Advertise on Noometry](https://noometry.com/advertise)

## Benchmark results

Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.

### Coding

DeepSeek-R1-Distill-Llama-70B Coding benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [BigCodeBench Instruct](https://noometry.com/benchmarks/bigcodebench-instruct) | 35.3% | #45 of 64, top 71% |  | [BigCodeBench](https://bigcode-bench.github.io/) | 2025-01-20 |
| [LiveBench Coding](https://noometry.com/benchmarks/livebench-coding) | 51.6% | #15 of 39, top 39% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [BigCodeBench Complete](https://noometry.com/benchmarks/bigcodebench-complete) | 49.9% | #35 of 66, top 54% |  | [BigCodeBench](https://bigcode-bench.github.io/) | 2025-01-20 |

### Reasoning

DeepSeek-R1-Distill-Llama-70B Reasoning benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [Kagi LLM Benchmark](https://noometry.com/benchmarks/kagi-reasoning) | 52.3% | #57 of 99, top 58% |  | [Kagi LLM Benchmark](https://help.kagi.com/kagi/ai/llm-benchmark.html) |  |
| [LiveBench Reasoning](https://noometry.com/benchmarks/livebench-reasoning) | 67.6% | #11 of 39, top 29% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LiveBench Data Analysis](https://noometry.com/benchmarks/livebench-data-analysis) | 55.9% | #17 of 39, top 44% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LiveBench](https://noometry.com/benchmarks/livebench) | 54.5% | #16 of 39, top 42% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

### Math

DeepSeek-R1-Distill-Llama-70B Math benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [OTIS Mock AIME 2024-2025](https://noometry.com/benchmarks/otis-mock-aime) | 51.4% | #112 of 173, top 65% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-03-07 |
| [LiveBench Math](https://noometry.com/benchmarks/livebench-math) | 58.1% | #15 of 39, top 39% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [MATH Level 5](https://noometry.com/benchmarks/math-level-5) | 89.9% | #15 of 79, top 19% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-03-10 |

### Knowledge

DeepSeek-R1-Distill-Llama-70B Knowledge benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [GPQA Diamond](https://noometry.com/benchmarks/gpqa-diamond) | 55.7% | #121 of 186, top 66% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-03-10 |

### Instruction Following

DeepSeek-R1-Distill-Llama-70B Instruction Following benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LiveBench Instruction Following](https://noometry.com/benchmarks/livebench-if) | 69.9% | #17 of 39, top 44% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

### Writing & Preference

DeepSeek-R1-Distill-Llama-70B Writing & Preference benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LiveBench Language](https://noometry.com/benchmarks/livebench-language) | 23.8% | #33 of 39, top 85% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

## Compare DeepSeek-R1-Distill-Llama-70B

-   [DeepSeek-R1-Distill-Llama-70B vs Gemini 2.0 Flash-Lite](https://noometry.com/compare/deepseek-r1-distill-llama-70b-vs-gemini-2-0-flash-lite)
-   [DeepSeek-R1-Distill-Llama-70B vs MiniMax-M2.7](https://noometry.com/compare/deepseek-r1-distill-llama-70b-vs-minimax-m2-7)
-   [DeepSeek-R1-Distill-Llama-70B vs Hunyuan Standard 2025 02 10](https://noometry.com/compare/deepseek-r1-distill-llama-70b-vs-hunyuan-standard)
-   [DeepSeek-R1-Distill-Llama-70B vs Gemini Advanced 0514](https://noometry.com/compare/deepseek-r1-distill-llama-70b-vs-gemini-advanced)
-   [DeepSeek-R1-Distill-Llama-70B vs GPT-5-Codex](https://noometry.com/compare/deepseek-r1-distill-llama-70b-vs-gpt-5-codex)
-   [DeepSeek-R1-Distill-Llama-70B vs Grok 2 Mini 2024 08 13](https://noometry.com/compare/deepseek-r1-distill-llama-70b-vs-grok-2-mini)
-   [DeepSeek-R1-Distill-Llama-70B vs GPT-6 Astra](https://noometry.com/compare/deepseek-r1-distill-llama-70b-vs-gpt-6-astra)
-   [DeepSeek-R1-Distill-Llama-70B vs Claude Fable 5.1](https://noometry.com/compare/claude-fable-5-1-vs-deepseek-r1-distill-llama-70b)
-   [DeepSeek-R1-Distill-Llama-70B vs Gemini 3.8 Flash](https://noometry.com/compare/deepseek-r1-distill-llama-70b-vs-gemini-3-8-flash)
-   [DeepSeek-R1-Distill-Llama-70B vs Kimi K3](https://noometry.com/compare/deepseek-r1-distill-llama-70b-vs-kimi-k3)
-   [DeepSeek-R1-Distill-Llama-70B vs Grok 4.6](https://noometry.com/compare/deepseek-r1-distill-llama-70b-vs-grok-4-6)
-   [DeepSeek-R1-Distill-Llama-70B vs Qwen3.8 Max](https://noometry.com/compare/deepseek-r1-distill-llama-70b-vs-qwen3-8-max)
-   [DeepSeek-R1-Distill-Llama-70B vs GLM-5.3](https://noometry.com/compare/deepseek-r1-distill-llama-70b-vs-glm-5-3)
-   [DeepSeek-R1-Distill-Llama-70B vs Muse Spark 1.3](https://noometry.com/compare/deepseek-r1-distill-llama-70b-vs-muse-spark-1-3)

## Other DeepSeek models

-   [DeepSeek V4 Pro](https://noometry.com/models/deepseek-v4-pro)54.3
-   [DeepSeek V4 Flash](https://noometry.com/models/deepseek-v4-flash)53.6
-   [DeepSeek V4.1 Flash](https://noometry.com/models/deepseek-v4-1-flash)52.8
-   [DeepSeek-V3.2-Exp](https://noometry.com/models/deepseek-v3-2-exp)44.3
-   [DeepSeek-V3.1-Terminus](https://noometry.com/models/deepseek-v3-1-terminus)43.1
-   [DeepSeek-V3.1](https://noometry.com/models/deepseek-v3-1)42.8
-   [DeepSeek-R1](https://noometry.com/models/deepseek-r1)42.3
-   [DeepSeek-V3.2-Speciale](https://noometry.com/models/deepseek-v3-2-speciale)39.7

## Frequently asked questions

### How good is DeepSeek-R1-Distill-Llama-70B?

DeepSeek-R1-Distill-Llama-70B by DeepSeek ranks 195th of 354 ranked models on the Noometry Index as of October 2026, with a score of 37.8. Its strongest category is reasoning, where it ranks 156th.

### Is DeepSeek-R1-Distill-Llama-70B open source?

Yes. DeepSeek-R1-Distill-Llama-70B's weights are downloadable; check the license for commercial terms.

### How fast is DeepSeek-R1-Distill-Llama-70B?

DeepSeek-R1-Distill-Llama-70B generated about 18 output tokens per second in the Kagi LLM Benchmark's timed runs. Speed varies by provider, load and reasoning effort.

### What are DeepSeek-R1-Distill-Llama-70B's strengths and weaknesses?

Relative to other ranked models, DeepSeek-R1-Distill-Llama-70B places best in reasoning, math, coding and lowest in knowledge, instruction following, writing & preference.

### What is DeepSeek-R1-Distill-Llama-70B best at?

Its best category is reasoning, where it ranks 156th on Noometry.

### Cite this page

Noometry. (2026). DeepSeek-R1-Distill-Llama-70B benchmarks and pricing. Retrieved October 10, 2026, from https://noometry.com/models/deepseek-r1-distill-llama-70b

Quote Noometry with a link back to this page. It is also available in [Markdown](https://noometry.com/md/models/deepseek-r1-distill-llama-70b.md).