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

Multiple Choice Question Answering on ARC-Easy (test)

89.1Accuracy

TaT

-3.1230420.8194844.76268.70452Apr 30, 2022Dec 19, 2022Aug 10, 2023Mar 30, 2024Nov 19, 2024Jul 10, 2025Mar 1, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
89.1
2026.03
87.12
2026.03
85.31
2026.03
84.3
2026.03
83.99
2026.03
83.59
2026.03
80.09
2026.03
80.05
2026.03
78.5
2026.03
76.27
2026.03
75.27
2026.03
74.92
2026.03
71.72
2026.02
71.2
2023.04
70.2
2026.03
69.44
2026.02
68.3
2026.02
68.1
2024.11
67.34
2023.04
67.3
2024.11
67
2024.11
66.88
2024.11
66.75
2024.11
65.15
2024.11
64.65
2023.04
64.4
2026.03
62.75
2023.04
60.6
2024.11
60.14
2026.03
58.6
2024.07
58.2
2023.04
56.9
2026.02
54.8
2024.07
54.7
2026.03
54.53
2026.02
54.3
2024.07
52.4
2024.07
52.3
2024.11
52.23
2023.04
52.1
2026.02
52.1
2024.07
48.4
2026.03
46.61
2024.07
45
2026.02
44.95
2024.07
44.9
2024.07
44.3
2023.04
43.5
2024.07
43.1
2024.07
42.7
2023.04
37.4
2026.02
34.26
2026.02
28.28
2026.02
28.11
2026.02
28.03
2026.02
27.32
2022.04
0.6901
2022.04
0.6692
2022.04
0.6643
2022.04
0.659
2022.04
0.624
2022.04
0.5882
2022.04
0.5388
2022.04
0.5377
2022.04
0.5366
2022.04
0.5232
2022.04
0.4584
2022.04
0.424