Epoch AI: Models prefer their own outputs over human gold standard in 23 of 24 tests

BethMayBarnes · x · 2026-11-19

Epoch AI added a self-preference test to its model evaluations: six frontier models compared their own outputs against gold-standard human work without knowing which was which, given Epoch's full grading rubric.

Tasks spanned design (model performance, parity point) and research (chess variants, hidden messages), including Claude Fable 5.2, Claude Opus 5.5, and GPT-6.2 Astra. The finding flags a systematic self-preference risk for LLM-as-judge workflows.

Original post →

More from Models

Models channel →