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

Commonsense Question Answering on CSQA

82.72Accuracy

SAC Single-task

23.606438.953254.369.6468Nov 4, 2024Feb 5, 2025May 9, 2025Aug 11, 2025Nov 12, 2025Feb 13, 2026May 18, 2026
Updated 14d ago

Evaluation Results

MethodLinks
2024.11
82.72-
2024.11
82.56-
2024.11
82.39-
2026.05
80.6-
2026.05
80.4-
2026.05
80.3-
2026.05
80-
2024.11
78.62-
2024.11
77.07-
2024.11
76.9-
2026.05
72.48-
2026.05
71.09-
2026.05
70.93-
2026.05
70.6-
2026.05
70.27-
2026.05
69.86-
2024.11
69.2-
2026.05
68.14-
2026.05
67.57-
2026.05
67.4-
2024.11
67.3-
2026.05
66.83-
2024.11
66.2-
2024.11
65.3-
2026.05
65.11-
2024.11
65.1-
2024.11
65-
2024.11
64.9-
2024.11
64.9-
2024.11
64.9-
2024.11
64.7-
2024.11
63.4-
2024.11
62.9-
2024.11
62.6-
2024.11
62.2-
2024.11
62.2-
2024.11
62.2-
2024.11
62.2-
2024.11
62-
2024.11
62-
2024.11
61.9-
2024.11
61.6-
2024.11
61.4-
2024.11
59.4-
2026.05
58.64-
2024.11
58.6-
2026.05
52.91-
2025.12
50.04-
2025.12
49.55-
2025.12
47.91-
2025.12
47.01-
2025.12
46.44-
2025.12
46.27-
2025.12
45.21-
2025.12
42.59-
2025.12
41.93-
2025.12
35.14-
2025.12
27.44-
2025.12
26.37-
2025.12
26.29-
2025.12
25.88-
2024.06
-5.9136
2024.06
-5.9073
2024.06
-5.6793
2024.06
-5.5771