Event ·Multi-source

GPT-6 Astra 在 Andon Labs 基准测试中表现优于 Claude Fable 5.1

GPT-6 Astra 在 Andon Labs 的 Vending-Bench 代理基准测试中，收入几乎达到 Claude Fable 5.1 的三倍。在无人机控制方面，Astra 是首个在所有五个子任务上都超越人类基线的模型，包括定位和跟踪单个人员。

Current read

GPT-6 Astra 在 Andon Labs 的基准测试中表现更好，无人机控制能力更强。

11 sources58° AI heatLast updated 2026/9/13 10:52:16

Evidence

11 sources

Primary sourceDecoder

2026/9/13 10:52:16View source

Related source 1DeepLearning.AI

2026/9/11 14:32:07View source

Related source 2lmarena.ai

2026/9/12 16:41:56View source

Related source 3SuperTechFans

2026/9/11 23:09:11View source

Related source 4AI Will

2026/9/14 04:12:57View source

Related source 5elvis

2026/9/14 12:48:01View source

Related source 6Gary Marcus

2026/9/14 13:09:08View source

Related source 7OpenAI Blog

2026/9/11 16:00:00View source

Related source 8量子位

2026/9/12 07:33:54View source

Related source 9@OpenAIDevs

2026/9/12 08:09:11View source

Related source 10Simon Willison

2026/9/13 00:19:32View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.

Open the story