DeepSeek: R1 Distill Llama 70B

deepseek/deepseek-r1-distill-llama-70b

Context: 8,192In: $0.80/1MOut: $0.80/1M

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...

Intelligence
Coding
Agentic

Metric profile

Trend over time

No history yet — first sync only. Trends appear over time.

Classic evals (curated from model cards)

DeepSeek — manually maintained, may lag releases

MMLU-Pro
75%
GPQA Diamond
67%
MATH-500
95%