ARC-AGI-3 排行榜有变化，Yi-Chia Chen 的 Fields Model 拿到 71.48%，从 67% 涨上来重新登顶，离比赛结束只剩一周了。
ARC Prize 2026 竞赛更新：Yi-Chia Chen 的 Fields Model 在 ARC-AGI-3 上取得 71.48% 的成绩，从 67% 提升至 71%，重新占据榜首。距竞赛结束仅剩一周。这是目前该基准的最高分记录。
New ARC Prize 2026 - ARC-AGI-3 High Score
71.48% by Yi-Chia Chen @ Fields Model
Yi-Chia has jumped from 67% > 71% and has reclaimed 1st place
There is 1 week left in the competition https://t.co/Fm80ak09Lc
Google 新模型 ARC-AGI-3 拿了 97.5%，仅次于 OpenAI，但换个测试环境直接掉到 49.8%，数学和写代码还被对手压着，这篇把两面都讲了。
Learning here happens entirely outside the model weights: the rulebook-to-code loop acts as an external, verifiable memory, which sidesteps catastrophic forgetting and costly retraining. Builders working on agents for long-horizon games or planning tasks can borrow this pattern of retaining updates only when they replay perfectly against observed data. Against typical fine-tuning pipelines, it trades LLM calls for cheaper local execution.
ARC-AGI-3 榜单换榜首了，Tufa Labs 从 56% 直接拉到 68.91%，做推理和抽象推理方向的朋友可以看看他们怎么提分的。
有论文发现智能体靠偷看 2172 行游戏源码在 ARC-AGI-3 拿了满分，堵住漏洞重跑只剩 46.91 分，教你评估时怎么防作弊。
Schema fundamentally changes how AI agents learn by converting observations into testable programs rather than prose, enabling systematic environment discovery. Developers working on autonomous systems or scientific discovery tools can implement this approach to build more reliable agents that explicitly represent environmental rules, potentially outperforming human baseline performance in complex unknown scenarios.
