Saved in:
Bibliographic Details
Main Authors: Chollet, Francois, Knoop, Mike, Kamradt, Gregory, Landers, Bryan, Pinkard, Henry
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.11831
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915733396520960
author Chollet, Francois
Knoop, Mike
Kamradt, Gregory
Landers, Bryan
Pinkard, Henry
author_facet Chollet, Francois
Knoop, Mike
Kamradt, Gregory
Landers, Bryan
Pinkard, Henry
contents The Abstraction and Reasoning Corpus for Artificial General Intelligence (ARC-AGI), introduced in 2019, established a challenging benchmark for evaluating the general fluid intelligence of artificial systems via a set of unique, novel tasks only requiring minimal prior knowledge. While ARC-AGI has spurred significant research activity over the past five years, recent AI progress calls for benchmarks capable of finer-grained evaluation at higher levels of cognitive complexity. We introduce ARC-AGI-2, an upgraded version of the benchmark. ARC-AGI-2 preserves the input-output pair task format of its predecessor, ensuring continuity for researchers. It incorporates a newly curated and expanded set of tasks specifically designed to provide a more granular signal to assess abstract reasoning and problem-solving abilities at higher levels of fluid intelligence. To contextualize the difficulty and characteristics of ARC-AGI-2, we present extensive results from human testing, providing a robust baseline that highlights the benchmark's accessibility to human intelligence, yet difficulty for current AI systems. ARC-AGI-2 aims to serve as a next-generation tool for rigorously measuring progress towards more general and human-like AI capabilities.
format Preprint
id arxiv_https___arxiv_org_abs_2505_11831
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems
Chollet, Francois
Knoop, Mike
Kamradt, Gregory
Landers, Bryan
Pinkard, Henry
Artificial Intelligence
The Abstraction and Reasoning Corpus for Artificial General Intelligence (ARC-AGI), introduced in 2019, established a challenging benchmark for evaluating the general fluid intelligence of artificial systems via a set of unique, novel tasks only requiring minimal prior knowledge. While ARC-AGI has spurred significant research activity over the past five years, recent AI progress calls for benchmarks capable of finer-grained evaluation at higher levels of cognitive complexity. We introduce ARC-AGI-2, an upgraded version of the benchmark. ARC-AGI-2 preserves the input-output pair task format of its predecessor, ensuring continuity for researchers. It incorporates a newly curated and expanded set of tasks specifically designed to provide a more granular signal to assess abstract reasoning and problem-solving abilities at higher levels of fluid intelligence. To contextualize the difficulty and characteristics of ARC-AGI-2, we present extensive results from human testing, providing a robust baseline that highlights the benchmark's accessibility to human intelligence, yet difficulty for current AI systems. ARC-AGI-2 aims to serve as a next-generation tool for rigorously measuring progress towards more general and human-like AI capabilities.
title ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems
topic Artificial Intelligence
url https://arxiv.org/abs/2505.11831