ARC Prize 2024: Technical Report

TL;DR

The ARC Prize 2024 report highlights progress in AI generalization benchmarks, showcasing new techniques and insights from a global competition aimed at advancing towards artificial general intelligence.

Contribution

This paper introduces the ARC Prize 2024 competition, reviews top approaches, open-source tools, and discusses limitations and insights related to the ARC-AGI benchmark.

Findings

State-of-the-art score increased from 33% to 55.5%.

Frontier reasoning techniques like deep learning-guided program synthesis improved performance.

Insights into limitations of the ARC-AGI-1 dataset were shared.

Abstract

As of December 2024, the ARC-AGI benchmark is five years old and remains unbeaten. We believe it is currently the most important unsolved AI benchmark in the world because it seeks to measure generalization on novel tasks -- the essence of intelligence -- as opposed to skill at tasks that can be prepared for in advance. This year, we launched ARC Prize, a global competition to inspire new ideas and drive open progress towards AGI by reaching a target benchmark score of 85\%. As a result, the state-of-the-art score on the ARC-AGI private evaluation set increased from 33\% to 55.5\%, propelled by several frontier AGI reasoning techniques including deep learning-guided program synthesis and test-time training. In this paper, we survey top approaches, review new open-source implementations, discuss the limitations of the ARC-AGI-1 dataset, and share key insights gained from the competition.