by MetaRank #287Score 40.0
Llama Guard 3 is a Llama-3.1-8B pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM inputs (prompt classification)...
| Signal | Normalized | Weight | Contribution | Freshness |
|---|---|---|---|---|
Capabilities capability | 16.7 | 30% | 5.0 | 2026-05-10T07:45:28.165Z |
Pricing pricing_tier | 100.0 | 25% | 25.0 | 2026-05-10T07:45:28.165Z |
Context Window context_window | 81.2 | 15% | 12.2 | 2026-05-10T07:45:28.165Z |
Recency recency | 50.7 | 15% | 7.6 | 2026-05-10T07:45:28.165Z |
Output Capacity output_capacity | 20.0 | 15% | 3.0 | 2026-05-10T07:45:28.165Z |
| Capability | Supported |
|---|---|
| Vision | No |
| Reasoning | No |
| JSON Mode | No |
| Streaming | Yes |
| Function Calling | No |
| Web Search | No |