Global MMLU

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

3 models

Higher is better.

Higher is better. Bar colour: blue proprietary, orange open weights, green other.

Metric: Average accuracy
Tasks: Knowledge questions across 42 languages
Authors: Singh et al. (2024)
Source: Global MMLU: Understanding and addressing cultural and linguistic biases in multilingual evaluation ↗

Scores are as reported by model developers or evaluators and may use different settings (for example reasoning effort or tools). Compare with care.