AGI progress has stalled.
New ideas are needed.

Presented by Infinite Monkey Lab42

ARC-AGI 2024 High Scores

Grand Prize Goal 85%
MindsAI 39
alijs 32
Lyrialtus 28
LIGHT 28
Alexander Larko 27

Live leaderboard [Kaggle]

Details

ARC-AGI measures progress towards artificial general intelligence using a private evaluation dataset. ARC Prize 2024 is scored against this leaderboard and the Grand Prize is unlocked by any team that reaches at least 85%.

ARC Prize 2024 imposes intentional constraints: no internet access (so no GPT-4, Claude, etc.) to reduce leaking the test and Kaggle compute is fixed to target efficiency.

New high scores will be announced here: @arcprize

Submit ARC-AGI high score claims via Kaggle.

ARC-AGI-PUB 2024 High Scores

Ryan GreenblattOpen in new window 42% 43%
icecuber 2020 [Example]Open in new window 39% 17%
Claude 3.5 [Baseline]Open in new window 21% 14%
GPT-4o [Baseline]Open in new window 9% 5%
Gemini 1.5 [Baseline]Open in new window 8% 4.5%
Name / Score (public eval) / Verification Score (semi-private eval)

Learn more about ARC-AGI-Pub

Details

ARC-AGI-Pub is a secondary leaderboard measuring the ARC-AGI public evaluation set. No competitions or prizes are associated with this leaderboard. Its purpose to explore frontier model performance on ARC-AGI.

This leaderboard imposes no limitations on internet access and few limitations on compute. That means you can utilize state-of-the-art models.

Selected high score claims are verified using a semi-private evaluation set.

New high scores will be announced here: @arcprize

Submit ARC-AGI-Pub high score claims here.

Toggle Animation