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

Multiple Choice Question Answering on ARC Challenge (test)

82.17Accuracy

TaT

18.719635.192351.66568.1377Apr 30, 2022Dec 19, 2022Aug 10, 2023Mar 30, 2024Nov 19, 2024Jul 10, 2025Mar 1, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
82.17
2026.03
78.41
2026.03
75.55
2026.03
75.32
2026.03
73.81
2026.03
71.72
2026.03
70.09
2026.03
69.71
2026.03
66.42
2026.03
65.96
2026.03
65.3
2026.03
60.92
2026.03
59.9
2022.04
54.42
2022.04
54.4
2022.04
54.33
2026.03
53.5
2026.03
52.92
2026.03
50.1
2026.03
49.82
2022.04
47.41
2026.03
44.51
2022.04
42.58
2022.04
42.43
2022.04
39
2022.04
35.97
2024.11
35.15
2022.04
34.85
2024.11
34.39
2024.11
33.79
2024.11
33.28
2024.11
32.08
2024.11
31.91
2022.04
31.19
2022.04
30.21
2024.11
28.92
2026.02
26.11
2022.04
25.8
2026.02
25.77
2026.02
25.43
2026.02
25
2026.02
24.66
23.04
2024.11
21.16