LL

Llama 4 Scout

Multimodal modelLlama 4

Llama 4 Scout

Release date: 2025-04-05Updated: 2025-04-06 07:27:50909
Parameters
109B
Context length
1000K
Chinese support
Supported
Reasoning ability

Llama 4 Scout is an AI model published by Facebook AI研究实验室, released on 2025-04-05, for Multimodal model, with 109B parameters, and 1000K context length, requiring about 218GB storage, under the Llama4 License license, with a 79.60 score on MMLU.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

Llama 4 Scout

Model basics

Reasoning traces
Not supported
Thinking modes
Thinking modes not supported
Context length
1000K tokens
Max output length
4K tokens
Model type
Multimodal model
Modality (in / out)
Text, Image, Audio, Video → Text
Release date
2025-04-05
Model file size
218GB
MoE architecture
No
Total params / Active params
109B / N/A
Knowledge cutoff
No data
Llama 4 Scout

Open source & experience

Llama 4 Scout

Official resources

Llama 4 Scout

API details

API speed
4/5
No public API pricing yet.
Llama 4 Scout

Benchmark Results

Llama 4 Scout currently shows benchmark results led by MBPP (19 / 28, score 67.80), MMLU (51 / 65, score 79.60), MATH (33 / 42, score 50.30). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.

Thinking

General Knowledge

4 evaluations
Benchmark / mode
Score
Rank/total
79.60
51 / 65
58.20
107 / 126
ARC-AGI
Thinking Mode
0.50
65 / 65
ARC-AGI-2
Thinking Mode
0
57 / 59

Coding and Software Engineer

1 evaluations
Benchmark / mode
Score
Rank/total
67.80
19 / 28

Math and Reasoning

1 evaluations
Benchmark / mode
Score
Rank/total
50.30
33 / 42

Compare with other models

No curated comparisons for this model yet.

Want a custom combination? Open the compare tool

Llama 4 Scout

Publisher

Facebook AI研究实验室
View publisher details
Llama 4 Scout

Model Overview

Llama 4 Scout is an AI model published by Facebook AI研究实验室, released on 2025-04-05, for Multimodal model, with 109B parameters, and 1000K context length, requiring about 218GB storage, under the Llama4 License license, with a 79.60 score on MMLU.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code