Fortune reports OpenAI repeatedly revised GPT-6 Astra benchmark data, with some scores changing significantly
Original title:OpenAI 多次修改 GPT-6 Astra 基准测试数据,部分成绩一度大幅变化
AI summary
Fortune reported that OpenAI has repeatedly revised evaluation benchmark data since its September 3 GPT-6 Astra announcement: Astra's hallucination rate was once cut from 4.2% to 2% and then changed back.
Quick Facts
原文基于网页快照逐项梳理数据变动细节,并给出多方的不同解读,可用于理解基准测试成绩为何容易波动和引发质疑。
Related entities
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: Fortune reports OpenAI repeatedly revised GPT-6 Astra benchmark data, with some scores changing significantly. September 6, 2026. https://new.nat6.net/en/news/cmtphtttc01pkroxxh8pinzq2/