The ARC-AGI dataset is an AI benchmark that measures progress towards general intelligence by testing a system's ability to efficiently acquire new skills outside of its training data. It requires the test taker (human or AI) to deduce underlying rules through abstraction, inference, and prior knowledge rather than brute-force or extensive training. It was used as the basis of the ARC Prize competition and determined the final leaderboard in 2020, 2022, 2023, and 2024.
No results indexed yet — be the first to submit a score.
Submit a checkpoint and a reproduction script. We will run it, publish the score, and — if it takes the top — annotate the step on the progress chart with your name.