GPT-6 Astra drives a real Toyota Corolla through a cone course; Claude Fable 5.1 reaches 45%
What happened
DrivingBench 直接把 GPT-6 Astra、Claude Fable 5.1、Grok 4.6 和 GPT-5.6 Sol 接上了一辆真丰田卡罗拉的方向盘、油门和刹车，让它们在同一个锥桶赛道里各跑三圈。GPT-6 Astra 第二次尝试就跑完全程，用时 5 分 22 秒，API 调用费花了 7.74 美元。Claude Fable 5.1...
Coverage
Follow the reports to see the story from different sides.
- Hacker News front pagePickGPT-6 Astra drives a real Toyota Corolla through a cone course; Claude Fable 5.1 reaches 45%
DrivingBench gave GPT-6 Astra, Claude Fable 5.1, Grok 4.6, and GPT-5.6 Sol direct control of a real Toyota Corolla's steering, accelerator, and brakes on a cone course. GPT-6 Astra completed the course on its second attempt in 5:22, costing $7.74 in API fees. Claude Fable 5.1 peaked at 45% progress; Grok 4.6 and GPT-5.6 Sol never exceeded 11%. Each model got three attempts inside one continuous chat. The post doesn't disclose total course length, cone spacing, or whether a safety driver intervened. I'd hold off on the '100%' claim until the trajectory replay shows smooth driving vs. constant correction.