Llama 4 Scout
Llama 4 Scout is an open-weights AI model from Meta with an index score of 112 (GPT-4 = 100), rank 172 of 217.
11296–128Index score#172 of 217 models
$0.10/ $0.30Price per million tokensinput / output · via OpenRouter
1.31MContext windowtokens it reads at once
5 Apr 2025Released1 year 7 months ago
Where it sitson the frontier
Claude 3.5 Sonnet (Jun 2024) reached this score 9 months earlier.
Test resultsby area · tick = best by any model
Reasoning & knowledgeevidence
Mathsevidence
Codingno evidence yet
Agentsevidence
Professional workno evidence yet
Novel problemsevidence
Long tasksno evidence yet
Third-party results only, at the model’s best standard setting. Hover a bar for who ran it.
What others sayrank on 2 leaderboards
The Model Indexthird-party tests, our method#172of 217 · 112
Epoch Capabilities Indexoverall capability from many benchmarks#146of 231 · 127.8Best attop three among current models
Not in the top three among current models on any category we track.
Where to use itprices checked 18 Nov 2026
From the lab
API providers 2 · per 1M tokens, in / out
Run it yourself
Official weightsmeta-llama/Llama-4-Scout-17B-16E-Instruct↗Host prices from OpenRouter; going direct can differ.
Facts and sources
Released5 Apr 2025
Announcementabout.fb.com ↗
Release entryLlama 4 (Scout/Maverick)
Scored asLlama 4 Scout
Output speed–
Hugging Facemeta-llama/Llama-4-Scout-17B-16E-Instruct ↗