WHAT NEW IN X11.06 FRI

AI collections from X · 23 collections · 69,408 posts

Back to No.001 GPT-6 Astra in Practice: Tests, Use Cases, and FeedbackUpdated 18 hours ago
benchmarkIMAGE

Opus 5.5 benchmarks beat GPT-6 Astra in almost every eval

A leaked benchmark chart shows Opus 5.5 beating Fable 5.1 on every eval and GPT-6 Astra on almost all of them.

Chubby♨️
@kimmonismusArchived 2026.09.23Originally posted 2026.09.23
Opus 5.5 benchmarks beat GPT-6 Astra in almost every eval
Chubby♨️ @kimmonismusOriginally posted 2026.09.23
Open original on X

And here are the benchmarks! Opus 5.5 excels Fable 5.1 in literally every single eval and even GPT-6 Astra in almost every single one. Holy moly, this is going to be interesting! h/t @synthwavedd

This post quotes another post: x.com/kimmonismus/status/2102435059123056793

x.com/kimmonismus/status/2102435466348032027Archived 2026.09.23 10:28
Open original on X