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

Multiple-choice Question Answering on ARC Challenge

74.7Acc

Llama3.1-8B

31.17642.475553.77565.0745Jul 19, 2023Jan 6, 2024Jun 26, 2024Dec 14, 2024Jun 4, 2025Nov 22, 2025May 13, 2026
Updated 9d ago

Evaluation Results

MethodLinks
2026.02
74.7-
2026.02
74.5-
2026.02
71.67-
2026.02
68.24-
2024.04
66.22.5
2023.07
64.5-
2024.04
64.413.7
2023.07
64.2-
2024.04
63.32.4
2024.04
62.96
2024.04
62.98.3
2024.04
62.81.5
2026.02
61.12-
2026.02
60.6-
2026.02
60.26-
2026.02
60-
2026.02
59.83-
2026.02
59.74-
2026.02
59.66-
2026.02
59.48-
2024.04
57.41.3
2024.04
56.512.4
2023.07
55.2-
2026.03
54.96-
2024.04
54.12.3
2026.03
53.95-
2026.03
53.81-
2026.03
53.7-
2026.05
53.67-
2024.04
53.58.6
2026.03
53.16-
2026.03
52.49-
2026.02
51.59-
2026.02
51.07-
2023.07
49.5-
2025.12
46.9-
2026.02
46.7-
2025.12
46.5-
2025.12
46.5-
2026.05
46.42-
2025.12
46.4-
2026.02
46.35-
2026.02
46.35-
2025.12
46.3-
2025.12
46.3-
2026.02
46.27-
2025.12
46.2-
2026.02
46.18-
2026.02
46.01-
2025.12
45.9-
2026.02
45.75-
2024.04
45.51.7
2023.07
45.2-
2025.12
45.1-
2023.07
44.8-
2025.12
44.4-
2025.12
44.2-
2025.12
44-
2025.12
43.9-
2025.12
43.7-
2026.02
43.61-
2026.02
43.35-
2025.12
43.3-
2025.12
43.3-
2025.12
43.2-
2026.05
42.41-
2025.12
42.4-
2025.12
42.4-
2025.12
42-
2025.12
41.8-
2025.12
41.8-
2025.12
41.4-
2025.12
41.2-
2026.05
40.96-
2025.12
40.9-
2025.12
40.1-
2025.12
40.1-
2025.11
40.1-
2025.11
39.68-
2025.11
39.25-
2025.11
39.16-
2025.11
39.08-
2025.11
38.91-
2025.11
38.57-
2026.05
38.41-
2026.05
38.41-
2026.03
36.86-
2026.03
36.09-
2024.04
3627.4
2026.01
34.73-
2026.03
34.28-
2026.03
33.81-
2026.01
33.79-
2026.01
33.7-
2026.01
33.62-
2026.03
33.47-
2026.01
33.36-
2026.03
33.07-
2026.01
32.94-
2026.01
32.85-
Showing 100 of 133 rows