Provider logo

Llama 4 Scout

meta-llama/llama-4-scout
Provider logo

Llama 4 Scout

meta-llama/llama-4-scout

Llama 4 Scout, a 17 billion active parameter model with 16 experts, is the best multimodal model in the world in its class and is more powerful than all previous generation Llama models, while fitting in a single H100 GPU. Additionally, Llama 4 Scout offers an industry-leading context window of 10M and delivers better results than Gemma 3, Gemini 2.0 Flash-Lite, and Mistral 3.1 across a broad range of widely reported benchmarks.

Added Sep 5, 2025

Model weights

Context Window

328.0K

Max Output

65.5K

Input Price (Auto)

$0.085/1M

Output Price (Auto)

$0.46/1M

Cache Read (Auto)

$0.043/1M

Capabilities

Benchmarks

Performance metrics and benchmarks

Sourced from Artificial Analysis.

Intelligence Index

10.3

Better than 32% of models compared

Coding Index

8.2

Better than 7% of models compared

Agentic Index

1.1

Better than 3% of models compared

Reasoning

GPQA Diamond

Graduate-level scientific reasoning

58.7%

Better than 34% of models compared

HLE

Humanity's Last Exam

3.8%

Better than 11% of models compared

IFBench

Instruction-following benchmark

39.5%

Better than 37% of models compared

T²-Bench Telecom

Conversational AI agents in dual-control scenarios

15.5%

Better than 13% of models compared

AA-LCR

Long context reasoning evaluation

30.3%

Better than 36% of models compared

GDPval-AA

Economically valuable tasks

0.0%

CritPt

Research-level physics reasoning

0.0%

Coding

SciCode

Python programming for scientific computing

17.0%

Better than 16% of models compared

Terminal-Bench Hard

Agentic coding and terminal use

1.5%

Better than 16% of models compared

LiveCodeBench

Contamination-free coding benchmark

29.9%

Better than 35% of models compared

Math

AIME 2025

American Invitational Mathematics Examination 2025

14.0%

Better than 17% of models compared

AIME

American Invitational Mathematics Examination

28.3%

Better than 55% of models compared

Math-500

Diverse mathematical problem solving benchmark

84.4%

Better than 51% of models compared

Knowledge

MMLU-Pro

Professional and academic subject knowledge

75.2%

Better than 49% of models compared

AA-Omniscience Accuracy

Proportion of correctly answered questions

15.2%

AA-Omniscience Hallucination Rate

Rate of incorrect answers among non-correct responses

79.4%

Last updated Aug 16, 2026

Artificial Analysis

Providers

Auto routing is available for this model. Explicit provider selection is not available.

Loading provider options…

Compare Llama 4 Scout with similar models from the same provider or model family.