Skip to content

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
33.320%6.72026-08-08T13:41:07.022Z
Benchmarks
benchmark
39.930%12.02026-08-08T13:41:07.022Z
Pricing
pricing_tier
99.215%14.92026-08-08T13:41:07.022Z
Context Window
context_window
62.110%6.22026-08-08T13:41:07.022Z
Recency
recency
30.615%4.62026-08-08T13:41:07.022Z
Output Capacity
output_capacity
65.010%6.52026-08-08T13:41:07.022Z

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
推理
JSON模式
流式输出
函数调用
网页搜索

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

相关模型

相关

R1 Distill Llama 70B Tracker - Performance History | LM Market Cap