WHAT NEW IN X11.01 SUN

AI collections from X · 22 collections · 63,170 posts

gpt-6POST

GPT-6 Astra scores 80 on physics benchmark, then corrects answer key to 98

A Turkish post says GPT-6 Astra scored 80 on a physics benchmark, told experts the answer key was wrong, and after rechecking its score rose to 98.

Avenox
@AvenoxaiArchived 13 days agoOriginally posted 2026.10.15
Avenox @AvenoxaiOriginally posted 2026.10.15
Open original on X

GPT 6 Astra fizik benchmarkında 80 aldı. Sonra uzmanlara "cevap anahtarınız yanlış" dedi. Tekrar kontrol ettiler. Astra haklıymış. Yeni skor: 98 😂

This post quotes another post: “GPT-6 Astra overturns expert answers on physics benchmark, score rises to 98%”

x.com/avenoxai/status/2110657922355413199Archived 2026.10.18 16:04