Llama 4 Scout
by MetaRank #215Score 60.2
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...
Performance Overview
Score
60.2
Rank
#215
24h Change
+2
7d Change
-9
State
stableConfidence
highSignal Scores
| Signal | Normalized | Weight | Contribution | Freshness |
|---|---|---|---|---|
Capabilities capability | 66.7 | 20% | 13.3 | 2026-09-22T14:23:52.574Z |
Benchmarks benchmark | 58.7 | 30% | 17.6 | 2026-09-22T14:23:52.574Z |
Pricing pricing_tier | 99.7 | 15% | 15.0 | 2026-09-22T14:23:52.574Z |
Context Window context_window | 97.1 | 10% | 9.7 | 2026-09-22T14:23:52.574Z |
Recency recency | 35.5 | 15% | 5.3 | 2026-09-22T14:23:52.574Z |
Output Capacity output_capacity | 67.4 | 10% | 6.7 | 2026-09-22T14:23:52.574Z |
Top Drivers
neutral
Benchmarks
positive
Pricing
$0.30/M output tokens
$0.30
positive
Capabilities
Supports vision, tools, JSON mode, streaming
4/7
positive
Context Window
1.3M token context window
1.3M
Capabilities
| Capability | Supported |
|---|---|
| Vision | Yes |
| Reasoning | No |
| JSON Mode | Yes |
| Streaming | Yes |
| Function Calling | Yes |
| Web Search | No |
Pricing
Input / 1M tokens
$0.10
Output / 1M tokens
$0.30
Context Window
1311K
Max Output
16K