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

Question Answering on PopQA (Accuracy)

87.12Accuracy

NWCAD

27.21642.76858.3273.872Mar 17, 2025Jun 2, 2025Aug 19, 2025Nov 4, 2025Jan 21, 2026Apr 8, 2026Jun 25, 2026
Updated 17d ago

Evaluation Results

MethodLinks
2026.04
87.12
2026.04
85.69
2026.04
85.62
2026.04
85.12
2026.04
84.94
2026.04
84.12
2026.04
84.12
2026.04
83.81
2026.04
82.69
2026.04
82.38
2026.04
80.94
2026.06
80.91
2026.06
80.63
2026.04
80.31
2026.06
78.98
2026.06
78.56
2026.04
78.44
2026.04
77.88
2026.04
75.29
2026.04
74.62
2026.04
74.29
2026.04
74
2026.04
73.4
2026.04
72.8
2026.04
72.8
2026.04
72.5
2026.04
72.38
2026.04
71.8
2026.04
71.08
2026.04
70.65
2025.03
70
2025.03
70
2025.03
70
2026.04
69.05
2025.03
69
2026.04
68.88
2026.04
68.8
2025.03
68
2025.03
68
2025.03
68
2026.04
67.37
2025.03
67
2025.03
67
2026.06
66.98
2026.06
66.38
2025.03
66
2026.06
65.76
2026.04
65.68
2026.04
65.6
2026.04
65.2
2026.04
64.6
2026.04
64.37
2026.04
64.15
2025.03
64
2025.03
64
2026.04
63.6
2026.04
63.28
2026.04
63.19
2026.04
62.78
2026.04
62.4
2026.04
62.24
2026.04
60.85
2026.04
60.83
2026.04
60.37
2026.04
60.25
2026.04
59.8
2025.03
59
2025.03
59
2026.04
59
2026.06
58.68
2026.06
56.17
2026.06
55.97
2026.06
55.02
2026.04
54.92
2026.06
54.45
2026.04
53.24
2026.04
53.18
2026.06
52
2026.06
50.8
2026.06
42.8
2026.06
42.6
2026.06
41.74
2026.02
41.3
2026.06
40.8
2026.06
40.8
2026.02
39.57
2026.06
38.8
2026.06
38.2
2026.06
35.67
2026.06
35.6
2026.02
35.2
2026.06
35.2
2026.02
34.23
2026.06
33.8
2026.06
32.6
2026.06
31.8
2026.05
31.44
2026.06
31
2026.06
30.6
2026.05
29.52
Showing 100 of 158 rows