Fetching from the wire…
Public story · 2026-03-11 · source-backed
The first interactive reasoning benchmark: instead of input/output grids, agents face novel games in an ARC grid world where they must discover rules through trial and error, track state, and learn on the fly. Given METR showed SWE-bench PRs aren't mergeable and EsoLang-Bench proved memorization, ARC-AGI-3 could become the gold standard for measuring actual AI reasoning. ARC Prize
Each link below shares sources, entities, or timing with this story.
François Chollet works at ARC Prize Foundation / Shared entities / Same source / Shared topic / What happened next
Linked by a graph relationship (François Chollet works at ARC Prize Foundation); both cover AGI, ARC, Launches March; cite the same source (ARC Prize).
Shared entities / Same source / Shared topic / Earlier coverage
Both cover AGI, ARC, ARC Prize, Francois Chollet; cite the same source (ARC Prize); overlapping topics (arc-agi-3, become, chollet, francoi).
Shared entities / Same source domain / Shared topic / What happened next
Both cover AGI, ARC, ARC Prize, Bench; reported by the same outlet (arcprize.org); overlapping topics (agent, benchmark).
Shared entities / Same source / Shared topic / Earlier coverage
Both cover AGI, ARC, Francois Chollet; cite the same source (ARC Prize); overlapping topics (agent, arc-agi-3, benchmark, chollet, francoi).
Shared entities / Same source domain / Shared topic / What happened next / Tension
Both cover AGI, ARC, ARC Prize; reported by the same outlet (arcprize.org); overlapping topics (agent, arc-agi-3, benchmark, chollet).
Shared entities / Same source / Shared topic / Earlier coverage / Tension
Both cover AGI, ARC, ARC Prize; cite the same source (ARC Prize); overlapping topics (arc-agi-3, chollet).
Both cover AGI, ARC, ARC Prize; cite the same source (ARC Prize); overlapping topics (arc-agi-3, chollet).
Shared entities / Same source domain / Shared topic / Earlier coverage / Tension
Both cover AGI, ARC, Launches March; reported by the same outlet (arcprize.org); overlapping topics (agent, arc-agi-3, benchmark, chollet).