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)...
| 信号 | 标准化 | 权重 | 贡献 | 新鲜度 |
|---|---|---|---|---|
Capabilities capability | 16.7 | 30% | 5.0 | 2026-05-10T09:06:44.605Z |
Pricing pricing_tier | 100.0 | 25% | 25.0 | 2026-05-10T09:06:44.605Z |
Context Window context_window | 81.2 | 15% | 12.2 | 2026-05-10T09:06:44.605Z |
Recency recency | 50.7 | 15% | 7.6 | 2026-05-10T09:06:44.605Z |
Output Capacity output_capacity | 20.0 | 15% | 3.0 | 2026-05-10T09:06:44.605Z |
| 功能 | 支持 |
|---|---|
| 视觉 | 否 |
| 推理 | 否 |
| JSON模式 | 否 |
| 流式输出 | 是 |
| 函数调用 | 否 |
| 网页搜索 | 否 |