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

Multiple Choice Question Answering on OBQA

87.74Accuracy

QAP

11.320831.16045170.8396Mar 30, 2025May 24, 2025Jul 18, 2025Sep 11, 2025Nov 5, 2025Dec 30, 2025Feb 23, 2026
Updated 3d ago

Evaluation Results

MethodLinks
2025.03
87.740.43
2025.03
85.040.32
2025.03
84.360.34
2025.03
82.980.21
2025.03
81.620.44
2025.03
80.120.19
2025.03
77.60.4
2026.02
76.6-
2025.03
76.120.34
2026.02
75.2-
2025.03
74.940.64
2025.03
74.880.14
2026.02
74.2-
2025.03
73.40.14
2025.03
72.720.3
2026.02
72.6-
2026.02
72-
2026.02
71.6-
2026.02
71.4-
2026.02
69.2-
2026.02
68.8-
2025.03
67.520.45
2026.02
67.21-
2025.03
66.320.44
2026.02
65.6-
2026.02
65.6-
2026.02
65-
2026.02
63.6-
2026.02
62.4-
2026.02
61-
2026.02
59-
2026.02
58.8-
2025.03
58.720.33
2026.02
58.66-
2026.02
58-
2025.03
57.280.09
2025.03
56.880.35
2026.02
54.6-
2025.03
52.720.29
2025.03
52.480.1
2025.03
520.45
2026.02
51.8-
2025.03
51.040.1
2025.03
510.18
2026.02
50.4-
2026.02
48.6-
2026.02
46.8-
2026.02
45.6-
2026.02
44.2-
2026.02
42.32-
2026.02
42-
2026.02
41-
2026.02
40.94-
2026.02
40.6-
2026.02
40.4-
2026.02
31-
2025.03
28.90.27
2025.03
27.160.45
2026.02
20.37-
2026.02
16.6-
2026.02
14.26-