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

General Language Capability on BIG-bench 57 Task

48.7Accuracy (Weighted)

GAL 120B

39.23641.69344.1546.607Nov 16, 2022
Updated 3mo ago

Evaluation Results

MethodLinks
2022.11
48.745.3
2022.11
46.642.7
2022.11
43.442.6
2022.11
42.642.2
2022.11
39.638