Tibo@thsottiauxTurns out GPT-5.6 Sol 实际上在 ARC-AGI-3 上达到了 SOTA。 只需更改两个设置。你只需允许它进行推理，并借助我们的标准压缩实现，在多个上下文窗口上工作。
Turns out GPT-5.6 Sol is actually SoTA on ARC-AGI-3.
Just took two setting changes. You just have to allow it to reason and work over multiple context windows with the help of our canonical compaction implementation.
https://openai.com/index/how-two-settings-tripled-our-arc-agi-3-scores/
Turns out GPT-5.6 Sol 实际上在 ARC-AGI-3 上达到了 SOTA。 只需更改两个设置。你只需允许它进行推理，并借助我们的标准压缩实现，在多个上下文窗口上工作。
Turns out GPT-5.6 Sol is actually SoTA on ARC-AGI-3.
Just took two setting changes. You just have to allow it to reason and work over multiple context windows with the help of our canonical compaction implementation.
https://openai.com/index/how-two-settings-tripled-our-arc-agi-3-scores/