Papers & Research

ARC Prize releases ARC-AGI-2 benchmark and opens 2025 competition

Original title:Announcing ARC-AGI-2 and ARC Prize 2025

AI summary

ARC Prize officially released the harder ARC-AGI-2 benchmark, on which pure LLMs score 0% and o3-preview-low scores only about 4%, while every task was solved by at least 2 people within 2 attempts.

Key Takeaways

  • ARC Prize officially released the harder ARC-AGI-2 benchmark
  • on which pure LLMs score 0% and o3-preview-low scores only about 4%
  • while every task was solved by at least 2 people within 2 attempts.

Quick Facts

Published
Updated
Source
ARC Prize:官方博客
Category
Papers & Research
AI score
70
Read the original Read the full article at the original source
Why it matters

官方公布了新基准的题型、人类与 AI 的对比成绩和效率指标,读者可以据此理解当前推理系统与人类泛化能力的具体差距。

Source & copyright

This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.

Original article · AIHOT entry

How to Cite

When citing this article, keep the title, date, and permalink, and credit Orange News as the source.

Orange News: ARC Prize releases ARC-AGI-2 benchmark and opens 2025 competition. March 24, 2025. https://new.nat6.net/en/news/cmtyo2p2s03g7rog0zm42djwy/

View all →