Skip to content

Llama 4 Maverick

by MetaRank #114Score 70.4

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...

性能概览

评分
70.4
排名
#114
24小时变化
0
7天变化
-9
状态
stable
置信度
high

信号评分

信号标准化权重贡献新鲜度
Capabilities
capability
66.720%13.32026-11-07T03:34:33.987Z
Benchmarks
benchmark
75.530%22.62026-11-07T03:34:33.987Z
Pricing
pricing_tier
99.015%14.92026-11-07T03:34:33.987Z
Context Window
context_window
90.810%9.12026-11-07T03:34:33.987Z
Recency
recency
27.215%4.12026-11-07T03:34:33.987Z
Output Capacity
output_capacity
72.210%7.22026-11-07T03:34:33.987Z

主要驱动因素

positive
Benchmarks
positive
Pricing
$1.00/M output tokens
$1.00
positive
Capabilities
Supports vision, tools, JSON mode, streaming
4/7
positive
Context Window
524K token context window
524K

功能

功能支持
视觉是
推理否
JSON模式是
流式输出是
函数调用是
网页搜索否

价格

输入/百万令牌
$0.35
输出/百万令牌
$1.00
上下文窗口
524K
最大输出
33K

相关模型

相关

Llama 4 Maverick Tracker - Performance History | LM Market Cap