Meta AI
Meta AI

Llama 4 Scout

Model ID:meta-llama/llama-4-scout
2025-04-05Open Model
API
OverallNo.33

Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input (text and image) and multilingual output (text and code) across 12 supported languages. Designed for assistant-style interaction and visual reasoning, Scout uses 16 experts per forward pass and features a context length of 10 million tokens, with a training corpus of ~40 trillion tokens. Built for high efficiency and local or commercial deployment, Llama 4 Scout incorporates early fusion for seamless modality integration. It is instruction-tuned for use in multilingual chat, captioning, and image understanding tasks. Released under the Llama 4 Community License, it was last trained on data up to August 2024 and launched publicly on April 5, 2025.

Knowledge Cutoff
2024-08-31

The date this AI finished learning. It may not know about things that happened after this date.

Input → Output Format

The types of content this AI can receive, and what it can produce in return.

Context Memory
328KIN16KOUT

The maximum amount of text the AI can read and process in a single request. A larger number means it can handle longer documents or conversations.

Cost/1M Words
$0.08IN$0.3OUT

The cost of using this AI directly in your own application. Shown in USD per 1 million units of text (tokens).

AI Performance Evaluation

Reasoning Ability
AA Intelligence Index
14%↓25%
MMLU-Pro
75%↓7%
GPQA Diamond
59%↓23%
HLE
4.3%↓12%
Math
AA Math Index
14%↓60%
MATH-500
84%↓10%
AIME 2024
28%↓31%
AIME 2025
14%↓60%
Coding Ability
AA Coding Index
6.7%↓30%
LiveCodeBench
30%↓36%
SciCode
17%↓25%
TerminalBench
1.5%↓33%
Instruction Following
IFBench
40%↓18%
환각률 (HHEM)
7.7%↓3%
사실 일관성 (HHEM)
92%↑3%
Long Context
AA-LCR
26%↓38%
Agentic AI Ability
TAU2
16%↓56%
Speed
Standard Mode
134tok/sec↑56
First Output 0.46s
Artificial Analysis