ARC Prize says ARC-AGI-1, -2, and -3 show a progression in model capability

AIARC Prize says the relationships across ARC-AGI-1, ARC-AGI-2, and ARC-AGI-3 point to a natural progression. It says future benchmarks will help track progress and separate increasingly capable models.

ARC PrizeOfficial

@arcprize

View on X

Part of a thread · earlier post

The relationships across ARC-AGI-1, ARC-AGI-2, and ARC-AGI-3 point to a natural progression. Future benchmarks will help us continue measuring progress and distinguishing between increasingly capable models.

View all model scores: https://arcprize.org/leaderboard

Source details

ARC Prize · x.comPublished Oct 28, 12:05 PM ET · added here 12:22 PM ET

Original title: The relationships across ARC-AGI-1, ARC-AGI-2, and ARC-AGI-3 point to a natural progression. Future benchmarks will help us continue meas...

Topics

Evals & benchmarks Expert opinion