AI researcher: benchmarks without released training data are 100% meaningless

mjdramstead · x · 2026-09-09

Researcher Michael Dramstead posted a blunt reminder: if a benchmark's training data isn't provided, the results are "absolutely, completely 100% meaningless," urging the community to stop pretending otherwise. The remark targets opaque train/test splits that make leaderboard scores incomparable and vulnerable to contamination.

Original post →

More from Models

Models channel →