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

Commonsense Reasoning on Commonsense 8 Sub-Tasks

61.4Accuracy (8 Sub-Tasks)

LoRA

39.14444.92250.756.478Mar 13, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
61.455.5
2026.03
60.637.7
2026.03
58.350.4
2026.03
56.752.3
2026.03
56.355.3
2026.03
55.652.6
2026.03
55.546.8
2026.03
55.153.4
2026.03
54.256.3
2026.03
5443
2026.03
53.949.3
2026.03
53.253
2026.03
52.550.1
2026.03
51.538.4
2026.03
50.447.3
2026.03
49.341.6
2026.03
48.148.1
2026.03
47.834
2026.03
47.144.3
2026.03
46.429.9
2026.03
44.842.5
2026.03
40.350.2
2026.03
4045.3