Nemotron 3 Nano Beats Soofi on LBPP

JJitsev · x · 2026-07-16

This discussion focuses on the LBPP benchmark results. The key point is that this benchmark falls outside the training contamination scope of Soofi's "rewritten benchmark set," making the results more reliable.

The conclusion drawn is that Nemotron 3 Nano significantly outperforms Soofi on this uncontaminated benchmark, scoring 38.1 vs 31.0. Replies also point out that signs of this performance drop without using rewritten benchmark training data were already visible in Soofi's own report.

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

Original post →

More from Models

Models channel →