Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

MMLU-ProX

Benchmarks

Task NameDataset NameSOTA ResultTrend
Multitask Language UnderstandingMMLU-ProX non-EU languages (test)
Accuracy70.9
16
Multitask Language UnderstandingMMLU-ProX 24 official EU languages
Score73.1
14
Showing 2 of 2 rows