模型40

Epoch 用自动化报告基准测试 GPT-6.2 Astra

原标题:We ran GPT-6.2 Astra on an updated version of ‘Epoch Automation Reports’, our benchmark of realistic tasks drawn from Epoch AI’s own work...

Epoch AI@EpochAIResearch发布时间 (北京时间)

Epoch AI 用更新版 Epoch Automation Reports 基准测试了 GPT-6.2 Astra,其在 ECI 上与 Fable 5.2 打平但整体落后,相较 GPT-6 Astra 仅小幅提升。

中文译文尚未完成,先为你展示原文。

We ran GPT-6.2 Astra on an updated version of ‘Epoch Automation Reports’, our benchmark of realistic tasks drawn from Epoch AI’s own work. Here, GPT-6.2 Astra fell behind Fable 5.2, despite tying on ECI, and improved only slightly over GPT-6 Astra.

On relatively simple research projects, 6.2 Astra failed to target the core question and iterate effectively. On our AI data center research task, 6.2 Astra was overly cautious and omitted critical estimates, which would be unacceptable for a contractor.

Its writing was relatively strong compared to the other models we evaluated, but still below Epoch AI’s standards. We will release a full report on our updated version of Epoch Automation Reports in another post.

同一件事的其他报道1 篇