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

Multiple Choice Question Answering on MMLU (5-shot)

73.4Accuracy

EdgeJury

23.292836.301449.3162.3186Nov 3, 2023Mar 24, 2024Aug 14, 2024Jan 4, 2025May 26, 2025Oct 16, 2025Mar 8, 2026
Updated 16d ago

Evaluation Results

MethodLinks
2025.12
73.4
2025.12
70.5
2023.11
69.58
2025.12
69.3
2023.11
66.92
2025.12
66.8
2023.11
66.78
2023.11
66.43
2023.11
66.4
2025.12
66.4
2023.11
66.23
2023.11
66.16
2023.11
65.9
2023.11
65.05
2023.11
64.77
2025.12
64.2
2023.11
56.07
2023.11
55.38
2023.11
53.3
2023.11
52.6
2023.11
52.31
2023.11
51.72
2023.11
51.23
2023.11
50.97
2023.11
50.77
2023.11
49.84
2023.11
48.91
2026.03
46.64
2026.03
46.63
2026.03
46.59
2023.11
46.58
2026.03
46.56
2026.03
46.45
2026.03
46.23
2026.03
46.16
2026.03
46.06
2026.03
46.06
2026.03
45.98
2026.03
45.86
2026.03
45.86
2026.03
45.72
2026.03
44.98
2023.11
42.74
2023.11
41.61
2023.11
41.11
2023.11
40.63
2023.11
40.06
2023.11
38.96
2023.11
38.61
2023.11
38.58
2023.11
38.5
2023.11
38.47
2023.11
37.46
2023.11
36.85
2023.11
34.39
2026.03
30.93
2026.03
30.93
2023.11
30.31
2026.03
30.14
2026.03
30.07
2026.03
29.74
2026.03
29.67
2026.03
29.59
2026.03
29.24
2026.03
29.09
2026.03
29.04
2026.03
28.77
2026.03
28.67
2026.03
28.13
2026.03
28.13
2023.11
27.79
2023.11
26.2
2023.11
25.22