DeepSeek-R1-Distill-Llama-70B
flagshipcurrently routing · 4.2k rpm
131K tokens
Context
open
License
/ ABOUT
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 multiple benchmarks, including:
- AIME 2024 pass@1: 70.0 - MATH-500 pass@1: 94.5 - CodeForces Rating: 1633
The model leverages fine-tuning from DeepSeek R1's outputs, enabling competitive performance comparable to larger frontier models.
BENCHMARKS Artificial Analysis Index
Intelligence 16
Coding 11.4
Providers for DeepSeek-R1-Distill-Llama-70B
2 routes · sorted by uptimeClosedRouter routes requests to the providers best able to handle your prompt size and parameters, with automatic fallbacks to maximize uptime.
