Skip to main content
ModelScale

Multilingual benchmark

GMMLU leaderboard

Global MMLU. Every model the catalog carries a published GMMLU value for, ranked by that value.

CategoryMultilingual
MeasureAverage accuracy
TasksKnowledge questions across 42 languages
DifficultyMultilingual knowledge
Published byGlobal MMLU: Understanding and addressing cultural and linguistic biases in multilingual evaluation

MMLU-style knowledge evaluation across 42 high- and low-resource languages.

GMMLU ranking

1 model with a published GMMLU value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

Models ranked by their published Global MMLU value
RankModelProviderAverage accuracy
1Claude Opus 5Anthropic92.5

Evidence key: Observed

Rows are ordered by the value Global MMLU: Understanding and addressing cultural and linguistic biases in multilingual evaluation published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.

All leaderboards