DeepSeek Models
DeepSeek logo

R1 Distill Llama 70B

70B

by 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 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.

Chat with R1 Distill Llama 70B
Input Price$0.70/1M tokens
Output Price$1.05/1M tokens
Intelligence16.0
Coding11.4

Specifications

Technical details and pricing.

ProviderDeepSeek
Context Window131,072 tokens
Release DateJan 20, 2025
ModalitiesText

Benchmarks

12 benchmark scores from Artificial Analysis.

GPQA40.2%
MMLU Pro79.5%
HLE6.1%
LiveCodeBench26.6%
MATH 50093.5%
AIME 202553.7%
AIME67.0%
SciCode31.2%
LCR11.0%
IFBench27.6%
Tau221.9%
TerminalBench Hard1.5%

Composite Indices

Intelligence, Coding, Math

Standard Benchmarks

Academic and industry benchmarks

Frequently Asked Questions

What is R1 Distill Llama 70B good for?

Use R1 Distill Llama 70B for everyday tasks like writing, summarizing, brainstorming, and getting clear explanations.

How much does R1 Distill Llama 70B cost?

Pricing is based on usage. Current rates are $0.70/1M tokens for input and $1.05/1M tokens for output.

Can I try R1 Distill Llama 70B for free?

Yes. You can start a chat instantly and test the model before deciding on a plan.

Does R1 Distill Llama 70B support images or audio?

R1 Distill Llama 70B focuses on text-based tasks.

Benchmarks and pricing are sourced from Artificial Analysis where available. OpenRouter specs are used as a fallback.