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

Commonsense Question Answering on CommonSenseQA

88.9Accuracy

HUMAN

7.05228.30149.5570.799Mar 24, 2021Jan 16, 2022Nov 11, 2022Sep 6, 2023Jun 30, 2024Apr 25, 2025Feb 18, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2021.03
88.9
2025.06
87.96
2025.06
87.71
2025.06
87.71
2025.06
87.55
2025.06
87.47
2025.06
86.65
2024.07
85.8
2025.06
85.75
2025.06
84.73
2025.06
84.6
2025.06
84.52
2025.06
84.19
2024.07
84.1
2025.06
83.78
2025.06
83.62
2024.07
82.4
2024.05
82.31
2025.06
82.23
2024.05
80.92
2021.03
79.3
79.1
2026.02
78.71
2026.02
78.46
2024.05
78.3
2021.03
78.1
2024.05
77.81
2024.05
77.72
2024.05
77.31
2024.05
77.31
2024.05
77.31
2024.07
75
2024.05
74.45
2024.07
74.4
72.1
2024.07
71.2
2023.05
57.08
2023.05
56.91
2023.05
56.73
2023.05
56.1
2023.05
55.61
2023.05
54.95
2023.05
53.79
53.24
2023.05
52.83
2023.05
52.66
2023.05
52.5
2023.05
51.92
2023.05
51.52
2023.05
45.3
2025.02
41
2025.02
41
2026.01
32.84
2026.01
29.87
2026.01
29.81
2025.02
28.9
2025.02
28.9
2026.01
25.63
2025.02
24.8
2025.02
23
2025.02
23
2025.02
22
2025.02
22
2025.02
21.7
2025.02
21.7
2025.02
21.1
2025.02
21.1
2025.02
21.1
2025.02
20.3
2025.02
20.3
2025.02
20.3
2025.02
20.3
2026.01
20.23
2025.02
20
2025.02
20
2026.01
19.74
2025.02
19.5
2025.02
19.5
2025.02
18.6
2025.02
18
2025.02
18
2025.02
10.2
2025.02
10.2