WritingmateWritingmate
AI Model

Meta: Llama 4 Scout

Meta: Llama 4 Scout logoMeta
Text Generation
Vision
About Llama 4 Scout

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...

Specifications
Provider
Meta
Context Length
10,000,000 tokens
Input Types
text, image
Output Types
text
Category
meta-llama/llama-4-scout-17b-16e-instruct
Added
4/5/2025

Benchmark Performance

How Llama 4 Scout compares to its closest rivals across industry benchmarks

SWE-Bench Verified
Evaluates AI ability to resolve real GitHub issues from Python repositories

Metric: % Resolved

#21
gpt-oss-120b
26.0
#25
Gemini 2.0 flash
13.5
#26
9.1
#27
Qwen2.5-Coder 32B Instruct
9.0
Artificial Analysis Intelligence Index
Comprehensive comparison of AI models across intelligence, price, speed, and latency

Metric: Intelligence Index

#120
Solar Pro 2
30.0
#121
Qwen3 Omni 30B A3B
30.0
#123
Mistral Small 3.2
29.0
#124
Ministral 8B (Dec '25)
28.0
#125
Llama 4 Scout
This model
28.0
#126
Llama 3.1 405B
28.0
#127
Llama 3.3 70B
28.0
#128
Devstral Medium
28.0
#129
Ling-mini-2.0
28.0

Frequently Asked Questions

Common questions about Llama 4 Scout

Use Llama 4 Scout and 200+ more models

Access all the best AI models in one platform. No API keys, no switching between apps.