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

Commonsense Reasoning on MMT-47 Commonsense Reasoning

84.98Accuracy

LiMELoRA

77.200879.220481.2483.2596Feb 1, 2026
Updated 13d ago

Evaluation Results

MethodLinks
2026.02
84.98
2026.02
84.76
2026.02
84.5
2026.02
84.49
2026.02
84.44
2026.02
84.43
2026.02
84.18
2026.02
84.11
2026.02
84.08
2026.02
84.07
2026.02
83.84
2026.02
83.8
2026.02
83.53
2026.02
83.45
2026.02
83.27
2026.02
78.38
2026.02
77.5