GMMLU
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
GMMLU c
30.75Acc (Normalized)
22
GMMLU c
32Accuracy
7
GMMLU Spanish c
33.75Acc (Normalized)
7
GMMLU common 30 languages (test)
11.3XSim Score
7
GMMLU all 41 languages (test)
23.9XSim Score
7
GMMLU c
32Normalized Accuracy
3
GMMLU Spanish (test)
32.5Normalized Accuracy
3