Announcing ARC-AGI-3
The only unsaturated agentic intelligence benchmark in the world
Humans score 100%, AI <1%
This human-AI gap demonstrates we do not yet have AGI
Most benchmarks test what models already know, ARC-AGI-3 tests how they learn
ARC Prize Research Summit
So far, we’ve received 22 applications to speak and 130+ applications to attend with limited space
Applications to present close September 14
ARC Prize Research Summit 2026
October 23, 2026 - Boston, MA
The ARC Prize community comes together to share new work, challenge ideas, and advance the frontier of machine reasoning towards general intelligence
New ARC Prize 2026 - ARC-AGI-3 High Score
4.58% by @tufalabs
Tufa Labs open-sourced their ARC-AGI-3 solution to claim Milestone Prize #1. Others quickly built on top of it and pushed the scores higher. Now they’ve reclaimed 1st place.
