GPT-6 Astra maxes ARC-AGI-3 with compaction, but harnesses differ

mhmazur · x · 2026-09-04

Steven Heidel (OpenAI) showed GPT-6 Astra maxing out ARC-AGI-3 when compaction is enabled in the Responses API, beating Opus 5 and GPT-5.6 Sol. But mhmazur notes the comparison isn't apples to apples: Astra's score uses the new Provider Adapter harness (preserving opaque reasoning across requests and compaction), while Opus 5 and GPT-5.6 Sol were run on the Standard harness.

Related event: OpenAI's Responses API Compaction Pushes GPT-6 Astra to Full Marks on ARC-AGI-3(3 posts)→

Original post →

More from Models

Models channel →