GPT-5.6 Sol Achieves SOTA on ARC-AGI-3 via Context Compaction

daniel_mac8 · x · 2026-07-30

Developers discovered that with two key setting adjustments, the GPT-5.6 Sol model achieved State-of-the-Art (SOTA) performance on the ARC-AGI-3 benchmark.

The breakthrough relied on allowing the model to reason and work across multiple context windows using a canonical compaction implementation. Tests showed that this autocompaction mechanism is extremely effective for complex, long-horizon tasks.

Related event: GPT-5.6 Scores Triple on ARC-AGI-3 After Enabling Two API Settings(17 posts)→

Original post →

More from Models

Models channel →