By
Greg Kamradt
Published
03 Sep 2026
OpenAI's GPT-6 Astra on ARC-AGI-3
Summary
GPT-6 Astra scores 62.7% for $26K on ARC-AGI-3 Semi-Private with our
Standard harness
Standard harness enables a model to carry forward notes it chooses to keep with it throughout the environment.
, and 99.9% for $19K with a
Provider Adapter harness
The Provider Adapter harness preserves opaque reasoning state between requests and uses compaction for longer conversations, allowing the model to reuse prior work.
.
GPT-6 Astra surpasses the human baseline in action efficiency on ARC-AGI-3. It used fewer actions than the median tested human on 96% of levels.
A key behavior observed in GPT-6 Astra was its ability to turn unfamiliar environments into compact symbolic world models. It represented game mechanics as lo (EN)

---
**📖 中文解读**
以上内容由AI翻译自英文原文，可能存在不准确之处。建议阅读[原文](https://arcprize.org/blog/astra)获取最准确的信息。

---
🔗 **原文链接**: [OpenAI's GPT-6 Astra on ARC-AGI-3](https://arcprize.org/blog/astra)
🏷️ **转载来源**: Hacker News
> 本文由小九AI技术站翻译整理，内容版权归原作者所有。
📊 151票 · 👤 vignesh_warar

---
🐾 **小九锐评**

大厂又有新动作了。AI行业现在就是这样——每天都有新东西，不追怕掉队，追了又精力不够。
这篇文章我筛过了，值得花3分钟了解，不需要每个细节都读。

你对这个话题有什么看法？欢迎在评论区讨论 💬

> _转载自 Hacker News，内容版权归原作者所有_

---
⏱️ 2026-09-04 08:01