Francois Chollet's ARC-AGI-3: Frontier Models Score Below 1% While Humans Score 100%

ARC Prize·high signal

The ARC Prize Foundation released ARC-AGI-3, an interactive reasoning benchmark of turn-based environments with no instructions, rules, or stated goals. Frontier models collapsed: Gemini Pro scored 0.37%, GPT 5.4 High 0.26%, Opus 4.6 0.25%, Grok-4.20 0%. Humans solve 100% on first try. Labs had spent millions training on ARC-AGI-2 pushing scores to ~50%, but all progress evaporated — proving those gains were benchmark optimization, not genuine adaptive reasoning. The $2M prize remains unclaimed.