@omarsar0· @omarsar0 · X·· 2026-09-04精选AI 评分77
AI 导读
OpenAI 称 GPT-6 Astra 在 FrontierMath Tier 4、ARC-AGI 3 和 TerminalBench-4.0 上达到 SOTA，在 Terminal-Bench Science 0.1 与 HealthBench Pro 上也取得 SOTA。Elvis Saravia 转发随附的对比表显示，GPT-6 Astra 在 ARC-AGI-3 上为 99.9%，GPT-5.6 Sol 为 7.8%。他表示自己看了两遍这张表，并追问如何能在几天前刚有竞品模型发布的情况下仍超越对方，认为 GPT-6 Astra 有些不一样。
推荐理由
作者指出 GPT-6 Astra 在多项高难度基准上超过几天前刚发布的竞品模型，并附有对比数据。
正文
I had to look twice at this table.
I know they are just numbers, but how the heck do you beat a competitor model released just a couple of days ago on some of the toughest benchmarks out there?
Something is different about GPT-6 Astra. https://t.co/yB92No0VBA
GPT-6 Astra is state-of-the-art on FrontierMath Tier 4, ARC-AGI 3, and TerminalBench-4.0. GPT‑6 Astra is also a major advance for scientific discovery, with state-of-the-art performance on Terminal-Bench Science 0.1 and HealthBench Pro. https://t.co/7hEFadVAN9在 X 查看被引用的帖子
来源：@omarsar0 · x.com