DeepSeek R1 (Jan '25)

Last updated: Recently

Model Type

Text

Max Context

64K

Max Output

16,000 tokens

Parameter Scale

DeepSeek R1 is here: Performance on par with OpenAI o1, but open sourced and with fully open reasoning tokens. 64,000 token context window, maximum output of 16,000 tokens. Higher uptime with 2 providers. Includes independent benchmarks from Artificial Analysis.

Input Modality

text

Output Modality

text

Inference Speed

Latest Release Date

1/20/2025

SDK Ecosystem

artificial-analysismanufactureraa-bootstrap

Model Overview Fields

name

DeepSeek R1 (Jan '25)

Release date

1/20/2025

Performance

model_creator.name

DeepSeek

AA Evaluation Scores

AA Intelligence Index

18.8

AA Coding Index

15.9

AA Math Index

MMLU Pro

0.844

GPQA

0.708

HLE

0.093

LiveCodeBench

0.617

SciCode

0.357

Math-500

0.966

AIME

0.683333333333333

AIME 2025

0.68

IFBench

0.389795918367347

LCR

0.523333333333333

TerminalBench Hard

0.0606060606060606

TAU2

0.114035087719298

Output Speed (tokens/s)

TTFT (s)

First Answer Token (s)

DeepSeek

DeepSeek R1 (Jan '25)

$1.68/M$4.70/M

There are no reviews for this model yet.

artificial-analysismanufactureraa-bootstrap

0.0