# Llama 4 Scout ![Organization](https://img.shields.io/badge/Org-Meta-0064e0) ![Active](https://img.shields.io/badge/Active-17B%20MoE-1f6feb) ![Context](https://img.shields.io/badge/Context-10M%20tokens-1f6feb) ![Modality](https://img.shields.io/badge/Modality-Multimodal-8957e5) ![Weights](https://img.shields.io/badge/Weights-Open-2da44e) ![Released](https://img.shields.io/badge/Released-Apr%202025-555) > **Quick answer:** Llama 4 Scout is Meta's April 2025 open-weight multimodal MoE model featuring a 10M-token context window — the largest of any open-weight model at launch. It scores 90.7% on AI2 Reasoning Challenge and 74.3% on MMLU-Pro with 17B active parameters. Available under the Llama 4 License with open weights on Hugging Face. ## At a Glance **Where Llama 4 Scout leads** - 10M-token context window — largest of any open-weight model at launch - 90.7% AI2 Reasoning Challenge — strong multi-discipline scientific reasoning - 74.3% MMLU-Pro — competitive academic knowledge - Open weights — self-hostable - Multimodal: text and image inputs - MoE efficiency: 17B active params at inference **Where it lags** - 74.3% MMLU-Pro and 90.7% AI2 RC — below Llama 4 Maverick (80.5%, 93.8%) - 16.9% BigCodeBench — limited coding performance - Llama 4 License (not Apache 2.0) — commercial use restrictions apply **Best for:** Open-weight deployments requiring extremely long context (book-length documents, whole-repository analysis); tasks where the 10M context window is the primary requirement. ## What Llama 4 Scout Is Llama 4 Scout is Meta's efficient model in the Llama 4 family, prioritising maximum context length over peak accuracy. Its 10M-token context window is 10× that of Llama 4 Maverick and GPT-4.1 — making it uniquely suited for tasks that require processing an entire codebase, book, or document collection in a single pass. Like Maverick, Scout uses a Mixture of Experts (MoE) architecture with 17B active parameters, making inference efficient. However, Scout is designed with fewer experts (16 per token vs Maverick's 128) — enabling the extreme context extension at the cost of reduced peak accuracy. At 90.7% AI2 Reasoning Challenge and 74.3% MMLU-Pro, Scout is a capable model across academic knowledge tasks, but Maverick outperforms it on standard benchmarks. For tasks that don't specifically require the 10M context window, Llama 4 Maverick is the recommended choice within the Llama 4 family. ## Specifications | Field | Value | |---|---| | Organization | Meta | | Active parameters | 17B (MoE, 16 experts) | | Context window | 10,000,000 tokens | | License | Llama 4 License | | HuggingFace | [meta-llama/Llama-4-Scout-17B-16E-Instruct](https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct) | | Release date | April 5, 2025 | | Knowledge cutoff | January 2025 | | Modality | Text + Vision (multimodal) | | Architecture | MoE (Mixture of Experts) | ## Pricing Llama 4 Scout is available as open weights — free to download and self-host. Hosted API access is available via Meta AI and third-party providers (Together AI, Groq, etc.) at market rates. ## Context Window Llama 4 Scout has a **10,000,000-token context window** — roughly **7,500 pages** of text, or a large codebase in a single request. This is the largest context window of any open-weight model, and matches or exceeds all closed-source models except Gemini 1.5 Pro Extended. ## Public Benchmark Scores | Benchmark | Score | Source | Date | |---|---|---|---| | [AI2 Reasoning Challenge](/benchmarks/ai2-reasoning-challenge) | 90.7% | Benchgen evaluation | 2025-07 | | [MMLU-Pro](/benchmarks/mmlu-pro) | 74.3% | Benchgen evaluation | 2025-07 | | [BigCodeBench](/benchmarks/bigcodebench) | 16.9% | Benchgen evaluation | 2025-07 | ## Llama 4 Scout vs Alternatives | Model | Context | AI2 RC | MMLU-Pro | Weights | |---|---|---|---|---| | **Llama 4 Scout** | 10M | 90.7% | 74.3% | Open | | [Llama 4 Maverick](/models/meta/llama-4-maverick) | 1M | 93.8% | 80.5% | Open | | [GPT-4.1](/models/openai/gpt-4-1) | 1M | 97.1% | — | Closed | | [Gemini 2.5 Pro](/models/google/gemini-2-5-pro) | 1M | — | — | Closed | Scout vs Maverick: 10× larger context window; lower accuracy on standard benchmarks. Choose Scout when the 10M context window is a hard requirement; choose Maverick for better performance on standard tasks. ## Run Llama 4 Scout ```python # Via Together AI (hosted) from together import Together client = Together(api_key="YOUR_API_KEY") response = client.chat.completions.create( model="meta-llama/Llama-4-Scout-17B-16E-Instruct", messages=[{"role": "user", "content": "Analyse this entire codebase..."}], ) print(response.choices[0].message.content) ``` ## Related Models & Benchmarks - Compare: [Llama 4 Maverick](/models/meta/llama-4-maverick) · [GPT-4.1](/models/openai/gpt-4-1) · [Gemini 2.5 Flash](/models/google/gemini-2-5-flash) - Benchmarks: [AI2 Reasoning Challenge](/benchmarks/ai2-reasoning-challenge) · [MMLU-Pro](/benchmarks/mmlu-pro) ## Frequently Asked Questions

What is Llama 4 Scout?

Llama 4 Scout is Meta's April 2025 open-weight multimodal MoE model with 17B active params and a 10M-token context window — the largest of any open-weight model at launch.

Is Llama 4 Scout open source?

The weights are open and available on Hugging Face under the Llama 4 License. Review the license terms for commercial use restrictions.

What is Llama 4 Scout's context window?

Llama 4 Scout supports a 10,000,000-token context window — approximately 7,500 pages of text.

What is the difference between Llama 4 Scout and Maverick?

Scout has a 10M context window (vs 1M for Maverick); Maverick achieves higher benchmark scores (80.5% MMLU-Pro vs 74.3%). Both have 17B active parameters. Use Scout for extreme long-context tasks; Maverick for better accuracy on standard tasks.

--- *Specs from Meta's official Llama 4 announcement (April 5, 2025) and Benchgen evaluations. Last updated 2026-07-24.*

Llama 4 Scout — Evaluations

Evaluations