DataLearner logo
LL

Llama 4 Scout

Multimodal modelLlama 4

Llama 4 Scout

Release date: 2025-04-05Updated: 2025-04-06Views: 1,023
Parameters
109B
Context length
1000K
Multilingual
Supported
Reasoning ability
2/5

Llama 4 Scout is an AI model published by Facebook AI Research Lab, released on 2025-04-05, for Multimodal model, with 109B parameters, and 1000K context length, requiring about 218GB storage, 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
No data
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 / Not applicable
Knowledge cutoff
No data
Llama 4 Scout

Open source & experience

Code license
Weights license
- Commercial use permitted
Live demo
N/A
Llama 4 Scout

Official resources

Paper
DataLearnerAI blog
N/A
Llama 4 Scout

API details

API speed
4/5
💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.
Standard
TypeConditionInputOutput
Text-$0.080/ 1M tokens$0.300/ 1M tokens

“—” means the modality is not billed in that direction, or the vendor has not published a price for it.

Llama 4 Scout

Benchmark Results

Llama 4 Scout currently shows benchmark results led by MBPP (39 / 96, score 67.80), MMLU (56 / 124, score 79.60), MMMU (48 / 74, score 69.40). 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
Tool usage

General Knowledge

5 evaluations
Benchmark / mode
Score
Rank/total
MMLU
Standard Mode
79.60
56 / 124
MMLU Pro
Standard Mode
58.20
124 / 176
HLE
Standard Mode
3.80
533 / 563
ARC-AGI-1
Thinking Mode
0.50
147 / 147
ARC-AGI-2
Thinking Mode
0
133 / 136

Coding and Software Engineer

3 evaluations
Benchmark / mode
Score
Rank/total
MBPP
Standard Mode
67.80
39 / 96
LiveCodeBench
Standard Mode
29.90
220 / 250
SciCode
Standard Mode
21.30
129 / 130

Math and Reasoning

2 evaluations
Benchmark / mode
Score
Rank/total
MATH
Standard Mode
50.30
33 / 42
AIME2025
Standard Mode
14
204 / 215

General Evaluation

1 evaluations
Benchmark / mode
Score
Rank/total
GPQA Diamond
Standard Mode
58.70
384 / 462

Multimodal Understanding

2 evaluations
Benchmark / mode
Score
Rank/total
MMMU
unknown
69.40
48 / 74
MMMU-Pro
Standard Mode
52.90
191 / 227

Agent Level Benchmark

3 evaluations
Benchmark / mode
Score
Rank/total
τ²-Bench - Telecom
Standard ModeTools
15.50
256 / 264
τ³-Banking
Standard ModeTools
3.30
162 / 164
Terminal Bench Hard
Standard ModeTools
1.50
237 / 244

Instruction Following

1 evaluations
Benchmark / mode
Score
Rank/total
IF Bench
Standard Mode
39.50
220 / 282

AI Agent - Tool Usage

1 evaluations
Benchmark / mode
Score
Rank/total
Terminal-Bench 2.1
Standard ModeTools
3.70
185 / 192

Claw-style Agent Evaluation

1 evaluations
Benchmark / mode
Score
Rank/total
3.19
45 / 45
Llama 4 Scout

Publisher

Facebook AI Research Lab
Facebook AI Research Lab
View publisher details
Llama 4 Scout

Model Overview

Llama 4 Scout is an AI model published by Facebook AI Research Lab, released on 2025-04-05, for Multimodal model, with 109B parameters, and 1000K context length, requiring about 218GB storage, 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