←新闻详情

ARC Prize更新于 10月21日 22:46

ARC Prize 公布 DeepSeek V4.1 Flash 评测成绩

@deepseek_ai Here's our earlier thread about DeepSeek V4.1 Flash's scores on ARC-AGI-1 and ARC-AGI-2:

AI 导读

@deepseek_ai 这是我们此前关于 DeepSeek V4.1 Flash 在 ARC-AGI-1 和 ARC-AGI-2 上成绩的帖子: https://t.co/5GiIpSHF2l

引用

ARC Prize

@arcprize

DeepSeek V4.1 Flash from @deepseek_ai on ARC-AGI (Verified): - ARC-AGI-2: 72.9%, $0.13/task - ARC-AGI-1: 94.5%, $0.07/task DeepSeek V4.1 Flash beats V4 Flash's best scores by 5.5 points on ARC-AGI-1 and 11.5 on ARC-AGI-2, but costs about 250% more per task. https://t.co/DDOiSntuR0

查看原帖

正文

当前显示原文,中文全文译文尚未就绪。

@deepseek_ai Here's our earlier thread about DeepSeek V4.1 Flash's scores on ARC-AGI-1 and ARC-AGI-2:

来源

ARC Prize