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

Multi-task Language Understanding on MMLU (Accuracy)

94.7Accuracy

Claude-Sonnet-4.5

67.19274.333581.47588.6165Apr 23, 2025Jun 20, 2025Aug 17, 2025Oct 15, 2025Dec 12, 2025Feb 8, 2026Apr 8, 2026
Updated 9d ago

Evaluation Results

MethodLinks
2026.03
94.7
2026.03
93.9
2026.03
93.4
2026.03
93
2026.03
92.2
2026.03
92
2026.03
91.9
2026.03
91.72
2026.03
90.67
90.63
90.47
90.11
2026.03
90.1
2026.04
90.09
2026.04
90.09
2026.04
90.09
2026.04
89.86
2026.03
89.61
2026.03
89.6
2026.03
89.2
2026.03
89.2
2026.03
89
2026.03
87.64
2026.03
87.4
2026.03
86.24
2026.04
85.6
2026.03
85.3
2026.04
85.3
2026.03
85.2
2026.04
84.8
2026.03
84.75
2026.03
84.57
2026.03
84.49
2026.04
83.7
2026.03
83.61
2026.04
83.6
2026.03
83.5
2025.04
83.4
2026.04
83.4
2026.04
83.4
2025.08
83.32
2026.04
82.5
2026.04
82.5
2025.04
82
2025.08
81.79
2025.04
81.7
2025.08
81.52
2026.04
81.3
2026.03
81
2026.04
80.8
2025.08
79.96
2025.08
79.54
2025.08
79.39
2025.08
79.33
2026.03
79.2
2026.03
78.91
2025.08
78.89
2025.04
78.8
2025.04
78.5
2026.03
76
2026.03
75
2026.03
74.7
2026.01
74.4
2026.02
74.3
2026.03
74.1
2026.02
73.73
2026.03
73.02
2026.02
72.92
2026.02
72.82
2026.03
72.77
2026.02
72.52
2026.02
72.49
2026.03
72.28
2026.03
72.15
2026.03
72.11
2026.03
71.76
2026.03
70.96
2026.03
70.53
2026.03
70.5
2026.02
70.41
2026.02
70.36
2026.02
70.35
2026.02
70.27
2026.02
70.18
2026.02
70.15
2026.02
70.08
2026.02
69.94
2026.02
69.9
2026.03
69.71
2026.02
69.65
2025.04
69.4
2026.03
69.12
2026.03
68.71
2026.03
68.71
2025.04
68.6
2025.04
68.5
2025.12
68.36
2025.12
68.32
2025.12
68.3
2026.02
68.25
Showing 100 of 321 rows