模型60

Artificial Analysis 测得 GPT-6.2 Astra 与 GPT-6.2 Sol 幻觉率分别为 59% 和 55%

原标题:GPT-6.2 Astra and GPT-6.2 Sol hallucinate at a rate of 59% and 55% at max effort respectively, as measured by AA-Omniscience Hallucinatio...

Artificial Analysis@ArtificialAnlys发布时间 (北京时间)

Artificial Analysis 测得 GPT-6.2 Astra 和 GPT-6.2 Sol 在最大努力设置下的幻觉率分别为 59% 和 55%,指标为 AA-Omniscience Hallucination Rate。该指标衡量模型在广泛话题的事实性问题中不知道正确答案时仍进行猜测的倾向。

中文译文尚未完成,先为你展示原文。

GPT-6.2 Astra and GPT-6.2 Sol hallucinate at a rate of 59% and 55% at max effort respectively, as measured by AA-Omniscience Hallucination Rate. This measures the tendency of a model to guess when it does not know the correct answer to factual questions on a broad range of topics.

OpenAI / ChatGPT评测基准#评测/基准#OpenAI

同一件事的其他报道1 篇