GPT-5.6 Sets New Record on ARC-AGI-3, Delayed by Review

soumitrashukla9 · x · 2026-07-10

GregKamradt revealed that GPT-5.6 underwent a US government evaluation period four times longer than usual before release, likely an extended review requested by the government. He believes this delayed the launch but resulted in a more stable model checkpoint and more thorough testing analysis. Meanwhile, an official ARC Prize tweet showed that GPT-5.6 Sol achieved 7.8% on ARC-AGI-3, a new SOTA, making it the first frontier model to pass the ARC-AGI-3 game.

Related event: GPT-5.6 Sets New SOTA on ARC-AGI-3 and Exceeds 30% on GDP.pdf(16 posts)→

Original post →

More from Models

Models channel →