Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

GlobalMMLU

Benchmarks

Task NameDataset NameSOTA ResultTrend
Multitask Language UnderstandingGlobalMMLU
Accuracy73.3
18
Multilingual ReasoningGlobalMMLU
English Accuracy88.77
6
Multilingual KnowledgeGlobalMMLU
Accuracy82
4
Showing 3 of 3 rows