Nonprofit founded by François Chollet and Mike Knoop. Maintains the ARC-AGI benchmark series, designed to measure fluid intelligence and resist memorization by testing novel task generalization rather than crystallized knowledge. Runs open-source prize competitions to advance AGI research. ARC-AGI-3 introduces interactive, agentic environments measuring exploration efficiency against human baselines.
ARC Prize ran NVIDIA's first open vision-language flagship through its reasoning gauntlet, and the numbers reveal where hybrid Mamba-MoE models still trip.
ARC Prize's latest chart shows collapsing per-task costs on ARC-AGI benchmarks, with reasoning models now solving problems for pennies instead of tens of dollars.
ARC Prize awards its first Milestone #1 prizes for ARC-AGI-3, with Tufa Labs, Reki, and Md Boktiar Mahbub Murad open-sourcing the top-scoring agents on the world's hardest agentic benchmark.