Researcher Flags Data Contamination in SOOFI Model Evaluations

JJitsev · x · 2026-07-19

Researcher @JJitsev points out that the SOOFI model, which recently claimed superiority in German evaluations, suffers from severe evaluation data contamination.

SOOFI was exposed to most of the evaluation sets during training (including the test set for GPQA), whereas the baseline original Nemotron-3-Nano was not. Claiming "frontier-level" status by comparing this "cheating" method against a baseline model is entirely invalid.

Related event: European Open-Source Model SOOFI Accused of Eval Leakage and Overhype(11 posts)→

Original post →

More from Models

Models channel →