OpenAI@OpenAIGPT-5.6 Sol 已被用于解决数学中的开放问题。那为什么它在 ARC-AGI-3（一个 2D 拼图游戏基准测试）上表现挣扎？ 我们调查了。测试框架没有让它记住所学的内容。 我们发现，启用两个 API 设置后，我们的得分提高了两倍，而输出 token 减少了 6 倍。
GPT-5.6 Sol has been used to solve open problems in mathematics. So why was it struggling with ARC-AGI-3， a benchmark of 2D puzzle games？
We investigated. The harness was not letting it remember what it had learned.
We found that enabling two API settings tripled our scores with 6x fewer output tokens.
GPT-5.6 Sol 已被用于解决数学中的开放问题。那为什么它在 ARC-AGI-3（一个 2D 拼图游戏基准测试）上表现挣扎？ 我们调查了。测试框架没有让它记住所学的内容。 我们发现，启用两个 API 设置后，我们的得分提高了两倍，而输出 token 减少了 6 倍。
GPT-5.6 Sol has been used to solve open problems in mathematics. So why was it struggling with ARC-AGI-3， a benchmark of 2D puzzle games？
We investigated. The harness was not letting it remember what it had learned.
We found that enabling two API settings tripled our scores with 6x fewer output tokens.