Meta, open weights

# Llama 3-8B

> Llama 3-8B by Meta, released April 2024. Ranked #344 of 354 with a Noometry Index of 25.5. Scores, sources and comparisons.
- Canonical page: https://noometry.com/models/llama-3-8b
- Last updated: 2026-10-10
- Title: Llama 3-8B Benchmarks, Price & Rank (October 2026)

Llama 3-8B by Meta ranks 344th of 354 ranked models on the Noometry Index as of October 2026, with a score of 25.5. Its strongest category is long context, where it ranks 251st.

Last verified October 10, 2026

## Specifications

- **Noometry rank:** #344 of 354
- **Index score:** 25.5
- **Evidence:** Confirmed 34 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:** Not measured
- **Value:** Not ranked
- **Knowledge cutoff:** Unknown

## Category scores

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

Llama 3-8B category scores

1.  Coding 31.0
2.  Reasoning 14.3
3.  Math 8.8
4.  Knowledge 7.8
5.  Multilingual 30.8
6.  Instruction Following 58.4
7.  Long Context 34.2
8.  Writing & Preference 37.5
9.  0204060

Llama 3-8B category ranks
| Category | Score | Rank | Results |
| --- | --- | --- | --- |
| [Coding](https://noometry.com/best/coding) | 31.0 | #289 | 3 |
| [Reasoning](https://noometry.com/best/reasoning) | 14.3 | #326 | 3 |
| [Math](https://noometry.com/best/math) | 8.8 | #323 | 3 |
| [Knowledge](https://noometry.com/best/knowledge) | 7.8 | #308 | 2 |
| [Multilingual](https://noometry.com/best/multilingual) | 30.8 | #261 | 1 |
| [Instruction Following](https://noometry.com/best/instruction-following) | 58.4 | #260 | 1 |
| [Long Context](https://noometry.com/best/long-context) | 34.2 | #251 | 1 |
| [Writing & Preference](https://noometry.com/best/writing) | 37.5 | #256 | 3 |

## Strengths and weaknesses

Categories where Llama 3-8B places highest and lowest among the models ranked in each, with its score against that category's median.

### Strongest categories

Llama 3-8B: strongest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Writing & Preference](https://noometry.com/best/writing) | 37.5 | −16.3 | #256 of 312, top 83% |
| [Long Context](https://noometry.com/best/long-context) | 34.2 | −6.8 | #251 of 296, top 85% |
| [Coding](https://noometry.com/best/coding) | 31.0 | −7.7 | #289 of 340, top 85% |

### Weakest categories

Llama 3-8B: weakest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Math](https://noometry.com/best/math) | 8.8 | −27.7 | #323 of 327, top 99% |
| [Knowledge](https://noometry.com/best/knowledge) | 7.8 | −29.6 | #308 of 314, top 99% |
| [Reasoning](https://noometry.com/best/reasoning) | 14.3 | −9.3 | #326 of 350, top 94% |

## Closest competitors

The models ranked just above and below Llama 3-8B. When scores are this close, price and speed are often the better way to choose.

Models ranked closest to Llama 3-8B
| Model | Rank | Score | Blended $/M | Speed |  |
| --- | --- | --- | --- | --- | --- |
| [Claude 3 Haiku](https://noometry.com/models/claude-3-haiku) | #340 | 25.9 | — | 41 | [Compare](https://noometry.com/compare/claude-3-haiku-vs-llama-3-8b) |
| [Gemma 2 9B](https://noometry.com/models/gemma-2-9b) | #341 | 25.9 | — | — | [Compare](https://noometry.com/compare/gemma-2-9b-vs-llama-3-8b) |
| [Dolly 2.0-12b](https://noometry.com/models/dolly-2-0-12b) | #342 | 25.5 | — | — | [Compare](https://noometry.com/compare/dolly-2-0-12b-vs-llama-3-8b) |
| [GPT-4o mini](https://noometry.com/models/gpt-4o-mini) | #343 | 25.5 | $0.26 | 120 | [Compare](https://noometry.com/compare/gpt-4o-mini-vs-llama-3-8b) |
| [Claude 2.1](https://noometry.com/models/claude-2-1) | #345 | 25.2 | — | — | [Compare](https://noometry.com/compare/claude-2-1-vs-llama-3-8b) |
| [Claude 2](https://noometry.com/models/claude-2) | #346 | 25.0 | — | — | [Compare](https://noometry.com/compare/claude-2-vs-llama-3-8b) |
| [DeepSeek LLM 67B](https://noometry.com/models/deepseek-llm-67b) | #347 | 24.9 | — | — | [Compare](https://noometry.com/compare/deepseek-llm-67b-vs-llama-3-8b) |
| [Llama 13b](https://noometry.com/models/llama-13b) | #348 | 24.4 | — | — | [Compare](https://noometry.com/compare/llama-13b-vs-llama-3-8b) |

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 3-8B Coding benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [BigCodeBench Instruct](https://noometry.com/benchmarks/bigcodebench-instruct) | 31.9% | #54 of 64, top 85% |  | [BigCodeBench](https://bigcode-bench.github.io/) | 2024-04-18 |
| [LMArena Coding](https://noometry.com/benchmarks/arena-coding) | 1152 | #257 of 294, top 88% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [BigCodeBench Complete](https://noometry.com/benchmarks/bigcodebench-complete) | 28.8% |  |  | [BigCodeBench](https://bigcode-bench.github.io/) | 2024-04-18 |
| [BigCodeBench Complete](https://noometry.com/benchmarks/bigcodebench-complete) | 36.9% | #58 of 66, top 88% |  | [BigCodeBench](https://bigcode-bench.github.io/) | 2024-04-18 |
| [HumanEval+](https://noometry.com/benchmarks/humaneval-plus) | 56.7% | #32 of 45, top 72% |  | [EvalPlus](https://evalplus.github.io/leaderboard.html) |  |
| [HumanEval+](https://noometry.com/benchmarks/humaneval-plus) | 29.3% |  |  | [EvalPlus](https://evalplus.github.io/leaderboard.html) |  |
| [MBPP+](https://noometry.com/benchmarks/mbpp-plus) | 51.6% |  |  | [EvalPlus](https://evalplus.github.io/leaderboard.html) |  |
| [MBPP+](https://noometry.com/benchmarks/mbpp-plus) | 54.8% | #30 of 38, top 79% |  | [EvalPlus](https://evalplus.github.io/leaderboard.html) |  |

### Reasoning

Llama 3-8B Reasoning benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [Chess Puzzles](https://noometry.com/benchmarks/chess-puzzles) | 0% | #122 of 129, top 95% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-28 |
| [LMArena Hard Prompts](https://noometry.com/benchmarks/arena-hard-prompts) | 1133 | #258 of 297, top 87% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [DTBench](https://noometry.com/benchmarks/dtbench) | 43.9% | #148 of 151, top 99% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Adversarial NLI](https://noometry.com/benchmarks/anli) | 57.3% | #3 of 9, top 34% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Epoch Capabilities Index](https://noometry.com/benchmarks/epoch-capabilities-index) | 116.45 | #183 of 213, top 86% |  | [Epoch AI](https://epoch.ai/eci) | 2024-04-18 |
| [ForecastBench](https://noometry.com/benchmarks/forecastbench) | 58.6 | #46 of 72, top 64% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [ForecastBench](https://noometry.com/benchmarks/forecastbench) | 52.9 |  |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [WinoGrande](https://noometry.com/benchmarks/winogrande) | 75.7% | #22 of 43, top 52% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [WinoGrande](https://noometry.com/benchmarks/winogrande) | 65% |  |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

### Math

Llama 3-8B Math benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [OTIS Mock AIME 2024-2025](https://noometry.com/benchmarks/otis-mock-aime) | 1.9% | #162 of 173, top 94% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-30 |
| [LMArena Math](https://noometry.com/benchmarks/arena-math) | 1151 | #251 of 285, top 89% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [MATH Level 5](https://noometry.com/benchmarks/math-level-5) | 6.1% | #76 of 79, top 97% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-01-27 |

### Knowledge

Llama 3-8B Knowledge benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [GPQA Diamond](https://noometry.com/benchmarks/gpqa-diamond) | 26.1% | #179 of 186, top 97% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-01-27 |
| [LMArena Expert](https://noometry.com/benchmarks/arena-expert) | 1113 | #247 of 273, top 91% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [ARC (AI2) Challenge](https://noometry.com/benchmarks/arc-challenge) | 82.8% | #12 of 39, top 31% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [MMLU](https://noometry.com/benchmarks/mmlu) | 68.8% | #48 of 81, top 60% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [OpenBookQA](https://noometry.com/benchmarks/openbookqa) | 82.6% | #6 of 19, top 32% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [TriviaQA](https://noometry.com/benchmarks/triviaqa) | 67.7% | #20 of 25, top 80% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

### Multilingual

Llama 3-8B Multilingual benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Non-English](https://noometry.com/benchmarks/arena-non-english) | 1098 | #261 of 297, top 88% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Chinese](https://noometry.com/benchmarks/arena-chinese) | 1076 | #259 of 285, top 91% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena French](https://noometry.com/benchmarks/arena-french) | 1159 | #204 of 223, top 92% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena German](https://noometry.com/benchmarks/arena-german) | 1104 | #210 of 231, top 91% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Japanese](https://noometry.com/benchmarks/arena-japanese) | 967 | #203 of 211, top 97% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Korean](https://noometry.com/benchmarks/arena-korean) | 1004 | #201 of 213, top 95% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Russian](https://noometry.com/benchmarks/arena-russian) | 1109 | #256 of 283, top 91% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Spanish](https://noometry.com/benchmarks/arena-spanish) | 1173 | #199 of 226, top 89% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Instruction Following

Llama 3-8B Instruction Following benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Instruction Following](https://noometry.com/benchmarks/arena-instruction-following) | 1127 | #258 of 298, top 87% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Long Context

Llama 3-8B Long Context benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Longer Query](https://noometry.com/benchmarks/arena-longer-query) | 1128 | #260 of 291, top 90% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Writing & Preference

Llama 3-8B Writing & Preference benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Text](https://noometry.com/benchmarks/arena-text) | 1166 | #254 of 297, top 86% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Creative Writing](https://noometry.com/benchmarks/arena-creative-writing) | 1150 | #250 of 295, top 85% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Multi-Turn](https://noometry.com/benchmarks/arena-multi-turn) | 1152 | #253 of 295, top 86% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

## Compare Llama 3-8B

-   [Llama 3-8B vs Llama 2-13B](https://noometry.com/compare/llama-2-13b-vs-llama-3-8b)
-   [Llama 3-8B vs GPT-4o mini](https://noometry.com/compare/gpt-4o-mini-vs-llama-3-8b)
-   [Llama 3-8B vs Claude 2.1](https://noometry.com/compare/claude-2-1-vs-llama-3-8b)
-   [Llama 3-8B vs Dolly 2.0-12b](https://noometry.com/compare/dolly-2-0-12b-vs-llama-3-8b)
-   [Llama 3-8B vs Claude 2](https://noometry.com/compare/claude-2-vs-llama-3-8b)
-   [Llama 3-8B vs Gemma 2 9B](https://noometry.com/compare/gemma-2-9b-vs-llama-3-8b)
-   [Llama 3-8B vs DeepSeek LLM 67B](https://noometry.com/compare/deepseek-llm-67b-vs-llama-3-8b)
-   [Llama 3-8B vs GPT-6 Astra](https://noometry.com/compare/gpt-6-astra-vs-llama-3-8b)
-   [Llama 3-8B vs Claude Fable 5.1](https://noometry.com/compare/claude-fable-5-1-vs-llama-3-8b)
-   [Llama 3-8B vs Gemini 3.8 Flash](https://noometry.com/compare/gemini-3-8-flash-vs-llama-3-8b)
-   [Llama 3-8B vs Kimi K3](https://noometry.com/compare/kimi-k3-vs-llama-3-8b)
-   [Llama 3-8B vs Grok 4.6](https://noometry.com/compare/grok-4-6-vs-llama-3-8b)
-   [Llama 3-8B vs Qwen3.8 Max](https://noometry.com/compare/llama-3-8b-vs-qwen3-8-max)
-   [Llama 3-8B vs GLM-5.3](https://noometry.com/compare/glm-5-3-vs-llama-3-8b)

## 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 3-8B?

Llama 3-8B by Meta ranks 344th of 354 ranked models on the Noometry Index as of October 2026, with a score of 25.5. Its strongest category is long context, where it ranks 251st.

### Is Llama 3-8B open source?

Yes. Llama 3-8B's weights are downloadable; check the license for commercial terms.

### What are Llama 3-8B's strengths and weaknesses?

Relative to other ranked models, Llama 3-8B places best in writing & preference, long context, coding and lowest in math, knowledge, reasoning.

### What is Llama 3-8B best at?

Its best category is long context, where it ranks 251st on Noometry.

### Cite this page

Noometry. (2026). Llama 3-8B benchmarks and pricing. Retrieved October 10, 2026, from https://noometry.com/models/llama-3-8b

Quote Noometry with a link back to this page. It is also available in [Markdown](https://noometry.com/md/models/llama-3-8b.md).