# LLaMA 3 (8B/70B)

LLaMA 3 (8B/70B) is an AI model released by Meta on Apr 18 2024. It has 8B/70B parameters, an 8k context window and open weight.

## Facts

| Field | Value |
| --- | --- |
| Model | LLaMA 3 (8B/70B) |
| Developer | Meta |
| Release date | Thursday, Apr 18 2024 |
| Licensing | Open Weight |
| Parameters | 8B/70B |
| Context window | 8k |

## Tracked benchmark scores

| Benchmark | Score | Source | What it measures |
| --- | --- | --- | --- |
| HumanEval | 81.7% | Lab | 164 small Python problems: the AI is given a function's description and has to write the working function. This was the coding benchmark of the GPT-3.5 and GPT-4 era, before the field moved to fixing real bugs in real repositories. Higher is better. |
| MATH | 50.4% | Lab | accuracy on the original competition mathematics test set |
| MMLU | 82% | Lab | A 57-subject multiple-choice exam — history, law, medicine, maths — that was the standard measure of how much a model knows from 2020 until roughly 2024, when frontier scores crowded into the high 80s and labs moved on to harder tests. The scores here were published years apart under different testing setups, so read them as a historical record rather than a like-for-like ranking. Higher is better. |
| GSM8K | 93% | Lab | Grade-school maths word problems that take a few steps of arithmetic to work through. It separated the models of 2022 and 2023 sharply, then saturated. One caveat on the historical numbers: OpenAI included part of the GSM8K training set in GPT-4's pre-training mix, so GPT-4's score is not a clean few-shot result. Higher is better. |

## About LLaMA 3 (8B/70B)

Llama 3 launched on April 18, 2024 with 8B and 70B parameter models, each offered as pretrained and instruction-tuned checkpoints. Meta emphasized improvements in following instructions, coding, reasoning and reducing unnecessary refusals. The first release was text based, and its 8,192-token context window was separate from the much longer context introduced with Llama 3.1 later that year. The publisher benchmarks listed here use the 70B Instruct checkpoint.

Meta reported pretraining on more than 15 trillion tokens and introduced a larger tokenizer vocabulary than Llama 2. Developers could download the models for fine-tuning and self-hosting under the Llama 3 Community License. The launch also powered the updated Meta AI assistant, connecting the research model family to a consumer product without making the assistant and the raw checkpoints interchangeable.

## Questions and answers

### When was LLaMA 3 (8B/70B) released?

LLaMA 3 (8B/70B) was released by Meta on Thursday, Apr 18 2024.

### Who made LLaMA 3 (8B/70B)?

LLaMA 3 (8B/70B) was built by Meta. Develops the open-weight Llama series of models. Committed to open-source AI research.

### What benchmark scores did LLaMA 3 (8B/70B) get?

LLaMA 3 (8B/70B) reports 4 tracked benchmark scores — HumanEval: 81.7%; MATH: 50.4%; MMLU: 82%; GSM8K: 93%. Tracked scores may come from lab reports or independent benchmarks; source details accompany the benchmark data.

### What is the context window of LLaMA 3 (8B/70B)?

LLaMA 3 (8B/70B) has a context window of 8k. Providers may specify separate input and output token limits.

### How many parameters does LLaMA 3 (8B/70B) have?

LLaMA 3 (8B/70B) is reported at 8B/70B parameters.

### Is LLaMA 3 (8B/70B) open source?

Partly. LLaMA 3 (8B/70B) is an open-weight model: the trained weights are free to download and run locally or on your own infrastructure, but the training data and code are not fully released and the license may restrict some commercial uses. It is not open source in the strict sense.

### What came before and after LLaMA 3 (8B/70B)?

Meta's previous tracked release was Code Llama 70B on Jan 29 2024, 80 days earlier. It was followed by LLaMA 3.1 on Jul 23 2024.


---

Canonical page: https://aireleasetracker.com/model/meta/llama-3-(8b-70b)
Site index: https://aireleasetracker.com/llms.txt
Source: AI Release Tracker (https://aireleasetracker.com). Most benchmark scores come from lab launch material; gathered results identify the leaderboard that published them.
