TrendingTopic

ARC-AGI-3 as evidence against near-term AGI

March 25, 2026ARC Prize, François Chollet, Lisan al Gaib

ARC Prize says humans score 100% and AI under 1% on ARC-AGI-3, while François Chollet stresses the G in AGI means generalization to new tasks. Lisan al Gaib posts sub-1% scores for several models.

Humans score 100%, AI <1%
This human-AI gap demonstrates we do not yet have AGI
The G in AGI stands for "general".
General intelligence does not mean that you have been specifically trained
Gemini 3.1 Pro: 0.37%
ARC Prize
François Chollet
Lisan al Gaib
AGIbenchmarksevaluation

See what experts are saying right now

This finding is one of many signals tracked across Artificial Intelligence. The live feed updates every few hours with new expert voices, debates, and emerging ideas.

← Back to Artificial Intelligence