R1 Distill Llama 70B

DeepSeek R1 Distill Llama 70B is an AI model from DeepSeek.

Publisher: DeepSeek
Family: Deepseek
Context: 8K
Input
Output
Released: 20 Jan 2025

Cite

Notes

Only stored in your browser.

Attribution

Benchmark scores: AA OpenLLM LiveBench

Attribution policy →

Context

8K

Input

$0.70

/1M tok

Output

$1.10

/1M tok

Blended

$0.80

#334/ 461/1M · 3:1

Speed

0

#115/ 461tok/s

Price & speed via Artificial Analysis · ranked across tracked models

Reported on 19 evals across 7 domains - best 93.5% on MATH-500 · #34 of 190

Reported eval scores

19

AIME 2024: Problems from the American Invitational Mathematics Examination67

MATH Level 530.7

LiveBench - Instruction Following70.2

LiveBench - Coding55.5

LiveBench - Language29.5

Terminal-Bench (Hard)1.5

MuSR43.4

BIG-Bench Hard (BBH)56.3

Humanity's Last Exam (HLE)5.1

AIME 2025: Problems from the American Invitational Mathematics Examination53.7

GPQA Diamond26.5

LiveCodeBench26.6

τ²-bench (Tau²-bench)21.9