WHAT NEW IN X10.28 WED

AI collections from X · 22 collections · 58,924 posts

gpt-6IMAGE

Blueprint-Bench rerun: GPT-6 Sol and Luna scores after OpenAI bug

andonlabs reran Blueprint-Bench for GPT-6 Sol and Luna because of an OpenAI bug: Sol improved slightly while Luna made a large jump, with score charts included.

Andon Labs
@andonlabsArchived 2026.09.28Originally posted 2026.09.28
Blueprint-Bench rerun: GPT-6 Sol and Luna scores after OpenAI bug
Andon Labs @andonlabsOriginally posted 2026.09.28
Open original on X

OpenAI had a bug, so we reran Blueprint-Bench for GPT-6 Sol and Luna. Sol improved slightly; Luna made a massive leap!

This post quotes another post: “OpenAI fixes GPT-6 Sol and Luna image understanding regression”

x.com/andonlabs/status/2104312958881042699Archived 2026.09.28 09:56