Meta, open weights

# Llama 3-70B

> Llama 3-70B by Meta, released April 2024. Ranked #323 of 354 with a Noometry Index of 28.8. Scores, sources and comparisons.
- Canonical page: https://noometry.com/models/llama-3-70b
- Last updated: 2026-10-10
- Title: Llama 3-70B Benchmarks, Price & Rank (October 2026)

Llama 3-70B by Meta ranks 323rd of 354 ranked models on the Noometry Index as of October 2026, with a score of 28.8. Its strongest category is agentic & tool use, where it ranks 139th.

Last verified October 10, 2026

## Specifications

- **Noometry rank:** #323 of 354
- **Index score:** 28.8
- **Evidence:** Confirmed 31 results
- **Provider:** [![](/logos/meta.svg) Meta](https://noometry.com/providers/meta)
- **Released:** April 18, 2024
- **Weights:** Open weights
- **Reasoning:** Unknown
- **Context window:** —
- **Max output:** —
- **Input price:** Not listed
- **Output price:** Not listed
- **Blended price:** Not listed
- **Output speed:** 104 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.

Llama 3-70B category scores

1.  Coding 35.8
2.  Agentic & Tool Use 21.1
3.  Reasoning 18.0
4.  Math 12.8
5.  Knowledge 20.8
6.  Multilingual 33.6
7.  Instruction Following 62.5
8.  Long Context 35.6
9.  Writing & Preference 42.8
10.  020406080

Llama 3-70B category ranks
| Category | Score | Rank | Results |
| --- | --- | --- | --- |
| [Coding](https://noometry.com/best/coding) | 35.8 | #218 | 3 |
| [Agentic & Tool Use](https://noometry.com/best/agentic) | 21.1 | #139 | 1 |
| [Reasoning](https://noometry.com/best/reasoning) | 18.0 | #288 | 3 |
| [Math](https://noometry.com/best/math) | 12.8 | #305 | 3 |
| [Knowledge](https://noometry.com/best/knowledge) | 20.8 | #277 | 2 |
| [Multilingual](https://noometry.com/best/multilingual) | 33.6 | #251 | 1 |
| [Instruction Following](https://noometry.com/best/instruction-following) | 62.5 | #238 | 1 |
| [Long Context](https://noometry.com/best/long-context) | 35.6 | #240 | 1 |
| [Writing & Preference](https://noometry.com/best/writing) | 42.8 | #231 | 3 |

## Strengths and weaknesses

Categories where Llama 3-70B places highest and lowest among the models ranked in each, with its score against that category's median.

### Strongest categories

Llama 3-70B: strongest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Coding](https://noometry.com/best/coding) | 35.8 | −2.9 | #218 of 340, top 65% |
| [Writing & Preference](https://noometry.com/best/writing) | 42.8 | −10.9 | #231 of 312, top 75% |
| [Instruction Following](https://noometry.com/best/instruction-following) | 62.5 | −8.7 | #238 of 305, top 79% |

### Weakest categories

Llama 3-70B: weakest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Math](https://noometry.com/best/math) | 12.8 | −23.7 | #305 of 327, top 94% |
| [Agentic & Tool Use](https://noometry.com/best/agentic) | 21.1 | −9.2 | #139 of 154, top 91% |
| [Knowledge](https://noometry.com/best/knowledge) | 20.8 | −16.5 | #277 of 314, top 89% |

## Closest competitors

The models ranked just above and below Llama 3-70B. When scores are this close, price and speed are often the better way to choose.

Models ranked closest to Llama 3-70B
| Model | Rank | Score | Blended $/M | Speed |  |
| --- | --- | --- | --- | --- | --- |
| [Claude 3 Sonnet](https://noometry.com/models/claude-3-sonnet) | #319 | 29.0 | — | — | [Compare](https://noometry.com/compare/claude-3-sonnet-vs-llama-3-70b) |
| [Qwen2.5 7B Instruct](https://noometry.com/models/qwen2-5-7b-instruct) | #320 | 29.0 | $0.31 | — | [Compare](https://noometry.com/compare/llama-3-70b-vs-qwen2-5-7b-instruct) |
| [Llama 3.2 3B](https://noometry.com/models/llama-3-2-3b) | #321 | 28.9 | $0.12 | — | [Compare](https://noometry.com/compare/llama-3-2-3b-vs-llama-3-70b) |
| [Qwen1.5 4b Chat](https://noometry.com/models/qwen1-5-4b-chat) | #322 | 28.8 | — | — | [Compare](https://noometry.com/compare/llama-3-70b-vs-qwen1-5-4b-chat) |
| [GPT-4o](https://noometry.com/models/gpt-4o) | #324 | 28.6 | $4.38 | — | [Compare](https://noometry.com/compare/gpt-4o-vs-llama-3-70b) |
| [Ministral 8B](https://noometry.com/models/ministral-8b) | #325 | 28.2 | $0.15 | — | [Compare](https://noometry.com/compare/llama-3-70b-vs-ministral-8b) |
| [Gemma 3 4B](https://noometry.com/models/gemma-3-4b) | #326 | 28.1 | $0.05 | 72 | [Compare](https://noometry.com/compare/gemma-3-4b-vs-llama-3-70b) |
| [GPT-4.1 nano](https://noometry.com/models/gpt-4-1-nano) | #327 | 27.9 | $0.18 | 135 | [Compare](https://noometry.com/compare/gpt-4-1-nano-vs-llama-3-70b) |

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

Llama 3-70B Coding benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [BigCodeBench Instruct](https://noometry.com/benchmarks/bigcodebench-instruct) | 43.6% | #25 of 64, top 40% |  | [BigCodeBench](https://bigcode-bench.github.io/) | 2024-04-18 |
| [LMArena Coding](https://noometry.com/benchmarks/arena-coding) | 1206 | #239 of 294, top 82% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [BigCodeBench Complete](https://noometry.com/benchmarks/bigcodebench-complete) | 43.3% |  |  | [BigCodeBench](https://bigcode-bench.github.io/) | 2024-04-18 |
| [BigCodeBench Complete](https://noometry.com/benchmarks/bigcodebench-complete) | 54.5% | #21 of 66, top 32% |  | [BigCodeBench](https://bigcode-bench.github.io/) | 2024-04-18 |
| [HumanEval+](https://noometry.com/benchmarks/humaneval-plus) | 72% | #17 of 45, top 38% |  | [EvalPlus](https://evalplus.github.io/leaderboard.html) |  |
| [MBPP+](https://noometry.com/benchmarks/mbpp-plus) | 69% | #16 of 38, top 43% |  | [EvalPlus](https://evalplus.github.io/leaderboard.html) |  |

### Agentic & Tool Use

Llama 3-70B Agentic & Tool Use benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [Cybench](https://noometry.com/benchmarks/cybench) | 5% | #21 of 21, top 100% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

### Reasoning

Llama 3-70B Reasoning benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [Kagi LLM Benchmark](https://noometry.com/benchmarks/kagi-reasoning) | 35.1% | #88 of 99, top 89% |  | [Kagi LLM Benchmark](https://help.kagi.com/kagi/ai/llm-benchmark.html) |  |
| [LMArena Hard Prompts](https://noometry.com/benchmarks/arena-hard-prompts) | 1195 | #239 of 297, top 81% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [DTBench](https://noometry.com/benchmarks/dtbench) | 54.2% | #125 of 151, top 83% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Epoch Capabilities Index](https://noometry.com/benchmarks/epoch-capabilities-index) | 122.93 | #161 of 213, top 76% |  | [Epoch AI](https://epoch.ai/eci) | 2024-04-18 |
| [ForecastBench](https://noometry.com/benchmarks/forecastbench) | 57.1 | #61 of 72, top 85% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [WinoGrande](https://noometry.com/benchmarks/winogrande) | 83.5% | #9 of 43, top 21% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

### Math

Llama 3-70B Math benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [OTIS Mock AIME 2024-2025](https://noometry.com/benchmarks/otis-mock-aime) | 4.3% | #152 of 173, top 88% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-02-25 |
| [LMArena Math](https://noometry.com/benchmarks/arena-math) | 1218 | #225 of 285, top 79% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [MATH Level 5](https://noometry.com/benchmarks/math-level-5) | 22.6% | #62 of 79, top 79% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-01-27 |

### Knowledge

Llama 3-70B Knowledge benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [GPQA Diamond](https://noometry.com/benchmarks/gpqa-diamond) | 40.6% | #150 of 186, top 81% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-01-27 |
| [LMArena Expert](https://noometry.com/benchmarks/arena-expert) | 1149 | #235 of 273, top 87% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [MMLU](https://noometry.com/benchmarks/mmlu) | 79.3% | #20 of 81, top 25% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

### Multilingual

Llama 3-70B Multilingual benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Non-English](https://noometry.com/benchmarks/arena-non-english) | 1142 | #251 of 297, top 85% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Chinese](https://noometry.com/benchmarks/arena-chinese) | 1114 | #255 of 285, top 90% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena French](https://noometry.com/benchmarks/arena-french) | 1232 | #188 of 223, top 85% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena German](https://noometry.com/benchmarks/arena-german) | 1169 | #199 of 231, top 87% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Japanese](https://noometry.com/benchmarks/arena-japanese) | 1017 | #198 of 211, top 94% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Korean](https://noometry.com/benchmarks/arena-korean) | 1017 | #198 of 213, top 93% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Russian](https://noometry.com/benchmarks/arena-russian) | 1159 | #247 of 283, top 88% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Spanish](https://noometry.com/benchmarks/arena-spanish) | 1241 | #187 of 226, top 83% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Instruction Following

Llama 3-70B Instruction Following benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Instruction Following](https://noometry.com/benchmarks/arena-instruction-following) | 1194 | #240 of 298, top 81% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Long Context

Llama 3-70B Long Context benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Longer Query](https://noometry.com/benchmarks/arena-longer-query) | 1174 | #249 of 291, top 86% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Writing & Preference

Llama 3-70B Writing & Preference benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Text](https://noometry.com/benchmarks/arena-text) | 1221 | #237 of 297, top 80% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Creative Writing](https://noometry.com/benchmarks/arena-creative-writing) | 1210 | #228 of 295, top 78% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Multi-Turn](https://noometry.com/benchmarks/arena-multi-turn) | 1223 | #230 of 295, top 78% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

## Compare Llama 3-70B

-   [Llama 3-70B vs Llama 2-13B](https://noometry.com/compare/llama-2-13b-vs-llama-3-70b)
-   [Llama 3-70B vs Qwen1.5 4b Chat](https://noometry.com/compare/llama-3-70b-vs-qwen1-5-4b-chat)
-   [Llama 3-70B vs GPT-4o](https://noometry.com/compare/gpt-4o-vs-llama-3-70b)
-   [Llama 3-70B vs Llama 3.2 3B](https://noometry.com/compare/llama-3-2-3b-vs-llama-3-70b)
-   [Llama 3-70B vs Ministral 8B](https://noometry.com/compare/llama-3-70b-vs-ministral-8b)
-   [Llama 3-70B vs Qwen2.5 7B Instruct](https://noometry.com/compare/llama-3-70b-vs-qwen2-5-7b-instruct)
-   [Llama 3-70B vs Gemma 3 4B](https://noometry.com/compare/gemma-3-4b-vs-llama-3-70b)
-   [Llama 3-70B vs GPT-6 Astra](https://noometry.com/compare/gpt-6-astra-vs-llama-3-70b)
-   [Llama 3-70B vs Claude Fable 5.1](https://noometry.com/compare/claude-fable-5-1-vs-llama-3-70b)
-   [Llama 3-70B vs Gemini 3.8 Flash](https://noometry.com/compare/gemini-3-8-flash-vs-llama-3-70b)
-   [Llama 3-70B vs Kimi K3](https://noometry.com/compare/kimi-k3-vs-llama-3-70b)
-   [Llama 3-70B vs Grok 4.6](https://noometry.com/compare/grok-4-6-vs-llama-3-70b)
-   [Llama 3-70B vs Qwen3.8 Max](https://noometry.com/compare/llama-3-70b-vs-qwen3-8-max)
-   [Llama 3-70B vs GLM-5.3](https://noometry.com/compare/glm-5-3-vs-llama-3-70b)

## Other Meta models

-   [Muse Spark 1.3](https://noometry.com/models/muse-spark-1-3)54.8
-   [Muse Spark](https://noometry.com/models/muse-spark)50.6
-   [Muse Spark 1.2](https://noometry.com/models/muse-spark-1-2)50.3
-   [Muse Spark 1.1](https://noometry.com/models/muse-spark-1-1)49.9
-   [Muse Glimmer](https://noometry.com/models/muse-glimmer)41.7
-   [Codellama 70b Instruct](https://noometry.com/models/codellama-70b-instruct)33.7
-   [Llama 4 Maverick](https://noometry.com/models/llama-4-maverick)30.9
-   [Codellama 34b Instruct](https://noometry.com/models/codellama-34b-instruct)30.8

## Frequently asked questions

### How good is Llama 3-70B?

Llama 3-70B by Meta ranks 323rd of 354 ranked models on the Noometry Index as of October 2026, with a score of 28.8. Its strongest category is agentic & tool use, where it ranks 139th.

### Is Llama 3-70B open source?

Yes. Llama 3-70B's weights are downloadable; check the license for commercial terms.

### How fast is Llama 3-70B?

Llama 3-70B generated about 104 output tokens per second in the Kagi LLM Benchmark's timed runs. Speed varies by provider, load and reasoning effort.

### What are Llama 3-70B's strengths and weaknesses?

Relative to other ranked models, Llama 3-70B places best in coding, writing & preference, instruction following and lowest in math, agentic & tool use, knowledge.

### What is Llama 3-70B best at?

Its best category is agentic & tool use, where it ranks 139th on Noometry.

### Cite this page

Noometry. (2026). Llama 3-70B benchmarks and pricing. Retrieved October 10, 2026, from https://noometry.com/models/llama-3-70b

Quote Noometry with a link back to this page. It is also available in [Markdown](https://noometry.com/md/models/llama-3-70b.md).