Skip to content

Llama 4 Scout

by MetaRank #217Score 54.7

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...

Performance Overview

Score
54.7
Rank
#217
24h Change
0
7d Change
-63
State
stable
Confidence
high

Signal Scores

SignalNormalizedWeightContributionFreshness
Capabilities
capability
66.720%13.32026-08-08T12:27:31.877Z
Benchmarks
benchmark
51.630%15.52026-08-08T12:27:31.877Z
Pricing
pricing_tier
99.715%15.02026-08-08T12:27:31.877Z
Context Window
context_window
97.110%9.72026-08-08T12:27:31.877Z
Recency
recency
43.715%6.62026-08-08T12:27:31.877Z
Output Capacity
output_capacity
70.010%7.02026-08-08T12:27:31.877Z

Top Drivers

neutral
Benchmarks
positive
Pricing
$0.30/M output tokens
$0.30
positive
Capabilities
Supports vision, tools, JSON mode, streaming
4/7
positive
Context Window
1.3M token context window
1.3M

Capabilities

CapabilitySupported
VisionYes
ReasoningNo
JSON ModeYes
StreamingYes
Function CallingYes
Web SearchNo

Pricing

Input / 1M tokens
$0.10
Output / 1M tokens
$0.30
Context Window
1311K
Max Output
16K

Related Models

Related

Llama 4 Scout Tracker - Performance History | LM Market Cap