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

Commonsense Reasoning on CommonsenseQA (val)

82.06Accuracy

Qwen-1.5 14B (Teacher)

16.560833.565450.5767.5746May 30, 2024Jun 8, 2024Jun 17, 2024Jun 26, 2024Jul 5, 2024Jul 14, 2024Jul 23, 2024
Updated 3d ago

Evaluation Results

MethodLinks
2024.07
82.06
2024.05
80.1
2024.05
78.84
2024.05
78.3
2024.05
77.56
2024.05
77.48
2024.05
77.31
2024.05
77.31
2024.05
77.15
2024.05
76.9
2024.05
75.92
2024.05
75.68
2024.05
75.59
2024.05
73.71
2024.05
73.22
2024.05
72.65
2024.05
71.74
2024.05
71.25
2024.05
67.98
2024.05
67.73
2024.05
67.32
2024.07
66.75
2024.07
66.26
2024.07
65.27
2024.07
65.11
2024.05
64.95
2024.07
64.78
2024.07
64.7
2024.07
64.46
2024.05
64.29
2024.05
63.96
2024.05
63.8
2024.05
63.49
2024.05
63.47
2024.05
63.06
2024.05
61.55
2024.05
60.77
2024.05
60.69
2024.05
60.44
2024.05
58.8
2024.05
58.39
2024.05
58.07
2024.05
56.43
2024.07
52.17
2024.05
48.4
2024.07
25.39
2024.07
22.93
2024.07
22.93
2024.07
22.52
2024.07
20.88
2024.07
20.39
2024.07
19.08