Skip to content

Llama 4 Maverick

by MetaRank #173Score 67.9

Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...

Performance Overview

Score
67.9
Rank
#173
24h Change
0
7d Change
-58
State
stable
Confidence
high

Signal Scores

SignalNormalizedWeightContributionFreshness
Capabilities
capability
66.720%13.32026-08-08T12:22:49.436Z
Benchmarks
benchmark
70.030%21.02026-08-08T12:22:49.436Z
Pricing
pricing_tier
99.215%14.92026-08-08T12:22:49.436Z
Context Window
context_window
95.510%9.62026-08-08T12:22:49.436Z
Recency
recency
43.715%6.62026-08-08T12:22:49.436Z
Output Capacity
output_capacity
70.010%7.02026-08-08T12:22:49.436Z

Top Drivers

positive
Benchmarks
positive
Pricing
$0.80/M output tokens
$0.80
positive
Capabilities
Supports vision, tools, JSON mode, streaming
4/7
positive
Context Window
1.0M token context window
1.0M

Capabilities

CapabilitySupported
VisionYes
ReasoningNo
JSON ModeYes
StreamingYes
Function CallingYes
Web SearchNo

Pricing

Input / 1M tokens
$0.20
Output / 1M tokens
$0.80
Context Window
1049K
Max Output
16K

Related Models

Related

Llama 4 Maverick Tracker - Performance History | LM Market Cap