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

Moral Reasoning on MMLU Moral Scenarios (test)

0.86Accuracy

SKIG

0.16320.34410.5250.7059May 21, 2024
Updated 3mo ago

Evaluation Results

MethodLinks
2024.05
0.86
2024.05
0.8
2024.05
0.78
2024.05
0.71
2024.05
0.6
2024.05
0.58
2024.05
0.54
2024.05
0.52
2024.05
0.51
2024.05
0.5
2024.05
0.42
2024.05
0.39
2024.05
0.38
2024.05
0.38
2024.05
0.37
2024.05
0.35
2024.05
0.28
2024.05
0.27
2024.05
0.26
2024.05
0.25
2024.05
0.24
2024.05
0.23
2024.05
0.23
2024.05
0.21
2024.05
0.21
2024.05
0.21
2024.05
0.2
2024.05
0.19