Global MMLU Lite (Kaggle) leaderboard

Global MMLU Lite (Kaggle) is an external benchmark published by BenchLM. Kaggle reports an average across 16 language dimensions of Global MMLU Lite, with separate culturally sensitive and culturally agnostic results. Its evaluation set is described by the source as 400 test questions per language; source average of 16 language dimensions. The source rates its difficulty as multilingual multiple-choice knowledge.

Each model's result is published by BenchLM as source-published percentage score. ModelScale prints that value to 1 decimal place, exactly as published, and never converts or rescales it. This page ranks the 0 models that carry a published value, highest value first; a model the source never scored is left out rather than ranked at zero. The source does not state whether a higher value is the better result, so neither does this page.