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

Commonsense Question Answering on CosQA (test)

82Accuracy

Few-shot Accuracy

50.342458.561266.7874.9988Mar 1, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
82
2026.03
81.7
2026.03
81.64
2026.03
80.94
2026.03
76.42
2026.03
75.08
2026.03
74.24
2026.03
74.18
2026.03
73.34
2026.03
71.17
2026.03
66.83
2026.03
66.4
2026.03
64.89
2026.03
61.54
2026.03
61.53
2026.03
61.51
2026.03
59.73
2026.03
51.56