ARC-AGI is a benchmark of abstract visual puzzles designed by Francois Chollet to resist memorization and reward genuine on-the-fly reasoning. When OpenAI previewed o3 on December 20, 2024, it scored 75.7 percent on the semi-private ARC-AGI-1 set in a low-compute configuration and 87.5 percent when allowed far more compute to think. As the ARC Prize team noted, “ARC-AGI-1 took 4 years to go from 0% with GPT-3 in 2020 to 5% in 2024 with GPT-4o.” The jump from roughly 5 percent to the high 80s in a single model generation was the most dramatic single-benchmark leap of the reasoning era.