Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Social Commonsense Reasoning on SIQA (test)

83.3Accuracy

UL20B

45.75655.50365.2574.997May 10, 2022Jul 21, 2022Oct 1, 2022Dec 13, 2022Feb 23, 2023May 6, 2023Jul 18, 2023
Updated 4d ago

Evaluation Results

MethodLinks
2022.05
83.3
2022.10
83.2
2022.05
83.2
2022.10
81.4
2022.10
80.18
2022.10
79.89
2022.10
76.7
2022.10
75.96
2023.07
52.3
2023.07
50.9
2023.07
50.7
2023.07
50.4
2023.07
50.4
2023.07
50.3
2023.07
50.1
2023.07
48.9
2023.07
48.9
2023.07
48.5
2023.07
48.3
2023.07
47.2