German Data and Evaluations Skew Comparisons

JJitsev · x · 2026-07-16

This reply corrects a statement in a German model comparison: it should be "better than Nemotron" rather than "versus Nemotron". The author argues that Soofi inherently holds a significant advantage over Nemotron due to having more German training data.

Furthermore, if "rewritten German evaluations" are included in the comparison, using them to prove Soofi's strength over Nemotron becomes invalid. The evaluations themselves are already influenced by training data or language processing methods, distorting the comparative conclusions.

Related event: SOOFI benchmark claims challenged over leakage and baseline reporting(13 posts)→

Original post →

More from Models

Models channel →