Meta
Llama 4 Scout
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...
Introducing Llama 4Model Snapshot
ReleaseApr 5, 2025
Context327,680
Overall
Rank #356 across 566
10.0
Coding
Rank #207 across 222
8.2
Blended Price
Rank #78 across 371
$0.287/M
Strength Profile
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Benchmark Percentiles
Higher bars mean stronger relative placement.
Model Details
Runtime
Output Speed89.6 tok/s
First Token0.59s
Max Output16,384
Pricing
Blended$0.287/M
Input$0.175/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 10.0 | #356 |
| Artificial Analysis Coding Index | coding | 8.2 | #207 |
| Artificial Analysis Math Index | math | 14.0 | #221 |
| MMLU-Pro | reasoning | 75.2% | #179 |