A user says model quality has regressed, especially on long accurate lists

ivan_bezdomny · x · 2026-07-23

The poster says they don’t know exactly when it started, but believe the models have regressed significantly.

They add that consumer questions requiring long but accurate lists have always been a weak spot, and cite the same ChatGPT sports-teams ranking example as evidence.

Related event: Users Say ChatGPT Is Slipping on Simple Ranking Tasks(2 posts)→

Original post →

More from Models

Models channel →