TAAFT
Free mode
100% free
Freemium
Free Trial
Deals

Llama 4 Scout

Model family: LLaMA
Large Multimodal Model; MoE architecture (16 experts, 17B active, 109B total params), industry-leading 10M context window; Natively multimodal via early fusion; Fits on single H100 GPU (int4); Use cases: multi-document summarization, personalization, code reasoning.
Text Gen 7
Released: April 5, 2025

About Meta Platforms

We're connecting people to what they care about, powering new, meaningful experiences, and advancing the state-of-the-art through open research and accessible tooling.

Industry: Technology, Information and Media
Company Size: 78865
Location: Menlo Park, California, US
Website: ai.meta.com
View Company Profile

Benchmark scores

How Llama 4 Scout ranks on tracked AI benchmarks. Click any benchmark to see its full leaderboard.

32.8%
GPQA Diamond
Knowledge
57.2%
MMLU-Pro
Knowledge
74.3%
ChartQA
Multimodal
88.8%
DocVQA
Multimodal
94.4%
MathVista
Multimodal
70.7%
MMMU
Multimodal
69.4%
Compare across all benchmarks โ†’

Tools using Llama 4 Scout

Last updated: April 6, 2026
0 AIs selected
Clear selection
#
Name
Task