DeepSeek V4.1 Flash 1017 的 ARC-AGI 成绩
@deepseek_ai @baseten DeepSeek V4.1 Flash 1017's performance on ARC-AGI-1 and ARC-AGI-2:
摘要
@deepseek_ai @baseten DeepSeek V4.1 Flash 1017 在 ARC-AGI-1 和 ARC-AGI-2 上的表现： https://x.com/arcprize/status/2113318031954764273
摘要由模型根据原文撰写，以原文为准。
正文 · 原文
@deepseek_ai @baseten DeepSeek V4.1 Flash 1017's performance on ARC-AGI-1 and ARC-AGI-2:
DeepSeek V4.1 Flash 1017 from @deepseek_ai on ARC-AGI (Verified): - ARC-AGI-2: 78.1%, $0.16/task - ARC-AGI-1: 94.5%, $0.06/task The best ARC-AGI-2 scores for DeepSeek's Flash models rose from 61.4% (V4 Flash 0731) to 72.9% (V4.1 Flash) to 78.1% (V4.1 Flash 1017).在 X 查看被引用的帖子
来源：ARC Prize · x.com
引用原文
arcprize. @deepseek_ai @baseten DeepSeek V4.1 Flash 1017's performance on ARC-AGI-1 and ARC-AGI-2:[EB/OL]. (2026-11-03)[访问日期]. https://x.com/arcprize/status/2117360594550509655.