Semi-private evals with holdout sets are 'basically dead' as vendors hillclimb

xeophon · x · 2026-08-19

@xeophon argues that semi-private evals and evals with holdout sets are basically dead: data vendors will simply build synthetic environments to hillclimb the benchmarks. He sees only two viable paths going forward — fully open-source evals (e.g. MazeBench) or internal evals (e.g. Cursorbench). The take directly targets benchmark contamination through targeted optimization.

Original post →

More from Models

Models channel →