Gemma4-E4B More Prone to Errors in Multilingual Contexts

LChoshen · x · 2026-07-14

Researchers tested Gemma4-E4B on chess/TicTacToe-style tasks and found it is more prone to spatial relation errors in Arabic or Hebrew compared to English.

Specific failure modes include:

This indicates that the model's spatial reasoning capabilities can be inconsistent across different language inputs.

Original post →

More from Models

Models channel →