WHAT NEW IN X10.28 WED

AI collections from X · 22 collections · 58,925 posts

gpt-6IMAGE

Blueprint-Bench: GPT-6 Sol edges out 5.6 Sol as Grok 4.7 regresses

A third-party benchmark screenshot shows GPT-6 Sol slightly better than 5.6 Sol, Grok 4.7 slightly worse than 4.6, and GPT-6 Luna performing poorly.

Andon Labs
@andonlabsArchived 2026.09.25Originally posted 2026.09.25
Blueprint-Bench: GPT-6 Sol edges out 5.6 Sol as Grok 4.7 regresses
Andon Labs @andonlabsOriginally posted 2026.09.25
Open original on X

New Blueprint-Bench results: > GPT 6 Sol is slightly better than 5.6 Sol > Grok 4.7 is slightly worse than 4.6 > GPT 6 Luna didn't do well at all

x.com/andonlabs/status/2103189545600921641Archived 2026.09.25 10:03