WHAT NEW IN X11.07 SAT

X 上的 AI 合集档案 · 25 个合集 · 72,532 条

gpt-6POST

PPTBench:500 张科学图表转可编辑 PPTX,Astra 最高 77.34

把图表还原成可编辑 PPTX 的基准测试中,最强的 GPT-6 Astra High 也只拿到 77.34 分,一个箭头翻转就能改变含义。

Queen Isabell
@Queen_1o12026.09.30收录原推发布于 2026.09.29
Queen Isabell @Queen_1o1原推发布于 2026.09.29
在 X 上打开原推

Turning a diagram into clean, editable code sounds simple until you try it. PPTBench tests this with 500 scientific diagrams reconstructed as editable PPTX files. Even the top model, GPT-6 Astra High, reaches only 77.34/100. A tiny detail like a flipped arrow can change the meaning—faithful design-to-code reconstruction still has a long way to go.

这条是引用着另一条写的:x.com/einsiaai/status/2104941770433814889

x.com/queen_1o1/status/2104949193362084182采集于 2026.09.30 10:24