by DeepSeekRank #168Score 41.2
DeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-Instruct](/meta-llama/llama-3.3-70b-instruct), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The model combines advanced distillation techniques to achieve high performance across...
| 信号 | 标准化 | 权重 | 贡献 | 新鲜度 |
|---|---|---|---|---|
Capabilities capability | 33.3 | 20% | 6.7 | 2026-06-24T11:11:52.669Z |
Benchmarks benchmark | 39.9 | 30% | 12.0 | 2026-06-24T11:11:52.669Z |
Pricing pricing_tier | 99.2 | 15% | 14.9 | 2026-06-24T11:11:52.669Z |
Context Window context_window | 73.0 | 10% | 7.3 | 2026-06-24T11:11:52.669Z |
Recency recency | 38.8 | 15% | 5.8 | 2026-06-24T11:11:52.669Z |
Output Capacity output_capacity | 65.2 | 10% | 6.5 | 2026-06-24T11:11:52.669Z |
| 功能 | 支持 |
|---|---|
| 视觉 | 否 |
| 推理 | 是 |
| JSON模式 | 否 |
| 流式输出 | 是 |
| 函数调用 | 否 |
| 网页搜索 | 否 |