Llama 4 Scout
Meta AI (FAIR)Llama 4 Scout was released April 5, 2025 as a 17B active parameter mixture-of-experts model (109B total, 16 experts). Featured a 10M token context window — the longest of any production model at launch. Natively multimodal (text + image). Scored 89.3% on MMLU. Beat Gemini 2.0 Flash and GPT-4o on multiple benchmarks while being deployable on a single H100 GPU.
Benchmarks1
| Benchmark | Score |
|---|---|
| MMLU | 89.3% |
Llama Family5
| Model | Tier | Released | Input $/MTok |
|---|---|---|---|
| Llama 4 Maverick | 2025-04-05 | ||
| Llama 3.3 | 2024-12-06 | ||
| Llama 3.1 | 2024-07-23 | ||
| Llama 3 | 2024-04-18 | ||
| Llama 2 | 2023-07-18 |
Details
Model FamilyLlama
Generation4
Release Date2025-04-05
Context Window10M tokens
Capabilities3
tool-usevisionlong-context
Sources1
Tags
llamametaopen-weightmixture-of-expertslong-context