Llama 4 Scout

10M-token context.

Released

Apr 5, 2025

Price in / out

—

Blended $/1M

—

Context

Parameters: 109B / 17B active. License: Llama 4 Community.

Benchmark scoresvs Llama 4 Maverick

Benchmark	Score	Δ vs prior	Rank (current)	Configuration	Source
τ²-bench (Telecom)	15.5%	-2.3	#10 of 10	leaderboard	benchlm.ai ↗
Artificial Analysis Intelligence Index	10	-4.3	#11 of 11	leaderboard	benchlm.ai ↗

Llama versions

Timeline

Version	Released	$ in / out	τ²-bench	AA Index
Llama 4 MaverickSuperseded	2025-04-05	—	17.8%	14.3
Llama 4 ScoutSuperseded	2025-04-05	—	15.5%	10

Compare

Open the Comparison Lab with Llama 4 Scout and its open-weight peers pre-selected, then toggle any benchmark or model.

Every Llama version over time

Shipping with it?

Benchmarks are a starting point. If you run Llama 4 Scout in production, post what it does well and where it falls over; other founders are deciding right now.

Write about Llama 4 Scout

Current open-weight peers

All

gpt-oss-120bOpenAI Gemma 4 31BGoogle DeepMind DeepSeek V4 Pro$0.435 in Kimi K3$3 in Kimi K2.7 Code$0.6 in Mistral Medium 3.5Mistral AI