Benchmark

Arc

The Abstraction and Reasoning Corpus (ARC) is a benchmark designed to measure human-like general fluid intelligence through grid-based reasoning tasks. It consists of 800 tasks (400 training, 400 evaluation) where each task presents input-output grids that require understanding abstract patterns and transformations. Test-takers must produce exactly correct output grids for all test inputs in a task to solve it, with 3 trials allowed per test input. ARC aims to enable fair comparisons of general intelligence between AI systems and humans using priors designed to be as close as possible to innate human priors.