lmarena.ai(@lmarena_ai)

DeepSeek V4 Flash Thinking at 284B parameters (13B activated) shifts the Text Pareto frontier with $...

5.0内容质量
DeepSeek V4 Flash Thinking at 284B parameters (13B activated) shifts the Text Pareto frontier with $...

TL;DR · AI 摘要

核心要点

打开原文

Congrats again to @DeepSeek_AI on the open model progress! https://t.co/dHmi9pZnbM" / X

Don’t miss what’s happening

Image 1: Square profile picture
Image 1: Square profile picture

Arena.ai

@arena

DeepSeek V4 Flash Thinking at 284B parameters (13B activated) shifts the Text Pareto frontier with $0.14 input / $0.28 output per MToken. Congrats again to

@DeepSeek_AI

on the open model progress!

Image 2: Image
Image 2: Image

3:52 AM · Apr 24, 2026