HSWAG
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
HSWAG
0.975Accuracy
52
HSwag
53.27Normalized PLL Score
26
HSwag
96.3Accuracy
16
HSwag
82.52HSwag Accuracy
9
HSWAG Out-of-Domain (test)
42.88Accuracy
8
HSWAG French (test)
33.5Accuracy
4
HSWAG German (test)
28.78Accuracy
4