R1 Distill Llama 70B
by DeepSeekRank #232Score 40.7
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...
性能概览
评分
40.7
排名
#232
24小时变化
0
7天变化
-63
状态
stable置信度
high信号评分
| 信号 | 标准化 | 权重 | 贡献 | 新鲜度 |
|---|---|---|---|---|
Capabilities capability | 33.3 | 20% | 6.7 | 2026-08-08T13:41:07.022Z |
Benchmarks benchmark | 39.9 | 30% | 12.0 | 2026-08-08T13:41:07.022Z |
Pricing pricing_tier | 99.2 | 15% | 14.9 | 2026-08-08T13:41:07.022Z |
Context Window context_window | 62.1 | 10% | 6.2 | 2026-08-08T13:41:07.022Z |
Recency recency | 30.6 | 15% | 4.6 | 2026-08-08T13:41:07.022Z |
Output Capacity output_capacity | 65.0 | 10% | 6.5 | 2026-08-08T13:41:07.022Z |
主要驱动因素
positive
Pricing
$0.80/M output tokens
$0.80
negative
Benchmarks
negative
Capabilities
Supports reasoning, streaming
2/7
positive
Output Capacity
Up to 8K output tokens per request
8K
功能
| 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 |
价格
输入/百万令牌
$0.80
输出/百万令牌
$0.80
上下文窗口
8K
最大输出
8K