MetaOpen weightsT🖼
Llama 4 Maverick
Rank
#373 / 636
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...
Overall
13.3
higher is better
Intelligence
10
Coding
16.3
Math
19.3
Speed
108
tok/s
Latency
0.57s
lower is better
Input price
$0.26
/ 1M tokens
Output price
$0.91
/ 1M tokens
Context
1.0M
tokens
Source: openrouter, artificialanalysis, aider