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

Commonsense Reasoning on ARC Challenge (val)

91.7Accuracy

SKILL-MOE

88.47689.31390.1590.987Mar 7, 2025
Updated 1d ago

Evaluation Results

MethodLinks
2025.03
91.7
90.1
2025.03
89.3
2025.03
89
88.6