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

Commonsense Reasoning on Balanced COPA

70.7Accuracy

NITP

60.8263.38565.9568.515May 24, 2026
Updated 8d ago

Evaluation Results

MethodLinks
2026.05
70.7
2026.05
68.1
2026.05
65.6
2026.05
65.6
2026.05
62.9
2026.05
61.2