GPT-6 Astra hits 62.7% on ARC-AGI-3, 99.9% with new adapter harness, sets ARC-AGI-2 SOTA at 95%

BlackHC · x · 2026-09-04

ARC Prize's analysis of OpenAI's GPT-6 Astra shows record-breaking results across the ARC-AGI suite:

ARC Prize will now evaluate models with both harnesses wherever possible.

Related event: GPT-6 Astra tops ARC-AGI with 62.7% on standard tests, near-perfect under new framework(2 posts)→

Original post →

More from Models

Models channel →