François Chollet reviews GPT-6 Astra performance on ARC-AGI-3
Original title:GPT-6 Astra represents a step-function change in model capability for interactive reasoning problems...
AI summary
François Chollet wrote that GPT-6 Astra delivers a step-change in interactive reasoning, scoring 66% on ARC-AGI-3 with the standard harness and close to 100% with a continuous conversation harness and custom compaction, at about $360 per run.
Key Takeaways
- François Chollet wrote that GPT-6 Astra delivers a step-change in interactive reasoning
- scoring 66% on ARC-AGI-3 with the standard harness and close to 100% with a continuous…
- at about $360 per run.
Quick Facts
- Published
- Updated
- Category
- Opinion
- AI score
- 81
ARC Prize 作者基于自家标准 harness 的实测数据评估 GPT-6 Astra,读者可对比 66% 与近 100% 两种设置看模型与 harness 能力的边界变化。
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: François Chollet reviews GPT-6 Astra performance on ARC-AGI-3. September 4, 2026. https://new.nat6.net/en/news/cmtlyeuas0rigrow5d2jq4xb7/