HackerPapers

arXiv:2412.04604cs.AI

ARC Prize 2024: Technical Report

Francois Chollet, Mike Knoop, Gregory Kamradt, Bryan Landers

Early discovery. Linked by one identifiable commenter. This paper is outside the main ranking; a mention is not an endorsement.

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.

arXiv comments
Journal reference
DOI
Subjects
cs.AIArtificial Intelligence

On Hacker News

Linked by 1 identifiable commenter in 1 comment across 1 thread, from Dec 2024 to Dec 2024. Found in 1 HN submission from Sep 2025 to Sep 2025. Open submission discussions.

Comments linking this paper, per year.

Discussed in comments1 thread

  1. OpenAI O3 breakthrough high score on ARC-AGI-PUB 1 comment

    • | Name | Semi-private eval | Public eval | |--------------------------------------|-------------------|-------------| | Jeremy Berman | 53.6% | 58.5% | | Akyürek et al. | 47.5% | 62.8% | | Ryan Greenblatt | 43% | 42% | | OpenAI o1-preview (pass@1) | 18% | 21% | | Anthropic…

      throwaway71271View on HNParent context

Submitted to Hacker News

  • Show HN: CodeWords – Build automations by chatting with AI1 point0 comments

    Hey HN, Aymeric here, co-founder of Agemo and maker of CodeWords. Generating nice-looking UIs with AI has been democratized now thanks to tools like Lovable, v0 and bolt. Going from natural language to a complex back-end workflow is still an unsolved problem. We started our journey by researching neurosymbolic methods applied to software/code generation problems and it landed us a feature in the ARC-AGI report last year (https://arxiv.org/abs/2412.04604). We've now applied this research to…

Connected through shared HN threads, not inferred similarity or a recommendation.