DeepSeek V3 0324

Last updated: Recently

Model Type

Text

Max Context

164K

Max Output

16,384 tokens

Parameter Scale

DeepSeek V3, 685B parameter, mixture of experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. 163,840 token context window, maximum output of 16,384 tokens. Higher uptime with 6 providers. Includes independent benchmarks from Artificial Analysis.

Input Modality

text

Output Modality

text

Inference Speed

Latest Release Date

3/25/2025

SDK Ecosystem

artificial-analysismanufactureraa-bootstrap

Model Overview Fields

name

DeepSeek V3 0324

Release date

3/25/2025

Performance

model_creator.name

DeepSeek

AA Evaluation Scores

AA Intelligence Index

22.3

AA Coding Index

AA Math Index

MMLU Pro

0.819

GPQA

0.655

HLE

0.052

LiveCodeBench

0.405

SciCode

0.358

Math-500

0.942

AIME

0.52

AIME 2025

0.41

IFBench

0.410204081632653

LCR

0.41

TerminalBench Hard

0.151515151515152

TAU2

0.470760233918129

Output Speed (tokens/s)

TTFT (s)

First Answer Token (s)

DeepSeek

DeepSeek V3 0324

$1.20/M$1.25/M

There are no reviews for this model yet.

artificial-analysismanufactureraa-bootstrap

0.0