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

Language Understanding on MMLU (MMLU Accuracy)

90MMLU Accuracy

GD

52.591262.303172.01581.7269Oct 17, 2025Nov 23, 2025Dec 31, 2025Feb 7, 2026Mar 17, 2026Apr 24, 2026Jun 1, 2026
Updated 1d ago

Evaluation Results

MethodLinks
2026.04
90
2026.06
85.26
2026.06
83.86
2026.06
83.51
2026.06
82.81
2026.06
82.11
2026.06
82
2026.06
81.7
2026.06
81.4
2026.05
81.12
2026.06
80.7
2026.05
80.25
2026.05
80.24
2026.05
80.15
2026.06
79.3
2026.06
78.95
2026.06
78.95
2026.06
78.95
2026.05
78.82
2026.06
78.6
2026.06
78.6
2026.06
78.6
2026.06
77.89
2026.05
77.33
2026.05
77.31
2026.06
77.19
2026.05
76.86
2026.05
76.84
2026.05
76.66
2026.05
76.64
2026.05
75.85
2026.05
75.84
2026.05
75.73
2026.05
75.62
2026.05
74.58
2026.05
74.58
2026.06
74.39
2026.05
73.49
2026.05
73.49
2026.05
72.5
2026.05
72.5
2026.05
72.48
2026.05
72.48
2026.06
72.4
2026.06
71.4
2026.05
71
2026.05
71
2026.05
70.99
2026.05
70.99
2026.06
70.9
2026.05
70.26
2026.05
70.26
2026.05
70.13
2026.05
70.13
2026.05
69.94
2026.05
69.94
2026.05
69.6
2026.05
69.6
2026.05
68.43
2026.05
68.43
2026.05
68.39
2026.05
68.39
2026.06
68.3
2026.05
67.09
2026.05
67.09
2026.05
67.06
2026.05
67.06
2026.05
64.62
2026.05
64.61
62.74
2025.10
62.15
2025.10
62.15
2025.10
62.1
2025.10
62.05
2025.10
62.01
2025.10
61.9
2025.10
61.88
2025.10
61.87
2025.10
61.86
2025.10
61.85
2025.10
61.85
2025.10
61.78
2025.10
61.74
2025.10
61.67
2025.10
61.6
2025.10
61.6
2025.10
61.6
2025.10
61.54
2025.10
61.5
2025.10
61.4
2025.10
61.35
2025.10
61.3
2025.10
61.28
2025.10
61.1
2026.06
60.6
2026.05
55.69
2026.05
54.58
2026.05
54.57
2026.05
54.21
2026.05
54.03
Showing 100 of 147 rows