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...
性能概览
评分
67.9
排名
#173
24小时变化
0
7天变化
-58
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 | 66.7 | 20% | 13.3 | 2026-08-08T13:29:09.589Z |
Benchmarks benchmark | 70.0 | 30% | 21.0 | 2026-08-08T13:29:09.589Z |
Pricing pricing_tier | 99.2 | 15% | 14.9 | 2026-08-08T13:29:09.589Z |
Context Window context_window | 95.5 | 10% | 9.6 | 2026-08-08T13:29:09.589Z |
Recency recency | 43.7 | 15% | 6.6 | 2026-08-08T13:29:09.589Z |
Output Capacity output_capacity | 70.0 | 10% | 7.0 | 2026-08-08T13:29:09.589Z |
主要驱动因素
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
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
$0.20
输出/百万令牌
$0.80
上下文窗口
1049K
最大输出
16K