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

Multi-task Language Understanding on MMLU (ACC, F1)

92MMLU Accuracy

DIRECT QUERY

34.849.6564.579.35Dec 30, 2023
Updated 9d ago

Evaluation Results

MethodLinks
2023.12
9292
2023.12
8971
2023.12
8990
2023.12
8382
2023.12
7474
2023.12
7171
2023.12
6060
2023.12
5958
2023.12
5857
2023.12
5654
2023.12
4847
2023.12
4746
2023.12
4545
2023.12
3736