← LLM ModelsOpen SourceView on HF →→
R1 Distill Llama 70B
DeepSeek
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...
openrouter.ai ↗📖Context131K tokens
🚀Speed-
💵Input price$0.800/1M
💸Output price$0.800/1M
🧠Parameters70.554B
Benchmarks
Gray bar = dataset averageComposite ScoreScore = MMLU×20% + GPQA×30% + HumanEval×25% + SWE-Bench×25%-
HF Open LLM Leaderboard
IFEval · BBH · MATH · GPQA · MuSR · MMLU-Pro
Average
27.8
IFEvalInstruction following
43.4%avg 79.9
BBHBig Bench Hard
35.8%avg 48.7
MATH Lvl 5Competition mathematics
30.7%avg 37.8
GPQAGraduate-level science Q&A
2.0%avg 12.9
MuSRMultistep soft reasoning
13.3%avg 10.7
MMLU-ProProfessional knowledge
41.6%avg 40.0
Made by
🏢
DeepSeek
providerMore from DeepSeek
API Providers
Details
- Provider
- DeepSeek
- Parameters
- 70.554B
- Context
- 131K tokens
- Speed
- -
- Open Source
- Yes
- License
- Open (varies)
- Released
- Jan 2025

