Experts stunned as OpenAI's Astra posts a shocking ARC benchmark result

salahuddin · x · 2026-09-04

salahuddin calls OpenAI's early Astra benchmarks "incredible/shocking," saying the ARC result could indicate a genuine leap, and is eager to hear what François Chollet and the ARC team make of it. The specific claim, per burnytech: GPT-6 Astra reportedly scored 98.6% on ARC-AGI-3.

Related event: GPT-6 Astra Launches with Benchmark Leaks: ARC-AGI-3 Hits 98.6%(41 posts)→

Original post →

More from Models

Models channel →