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

Multitask Language Understanding on MMLU-Pro

89.31Accuracy

Gemini-3-Pro-Preview

62.883669.744376.60583.4657Jul 31, 2024Nov 19, 2024Mar 10, 2025Jun 29, 2025Oct 18, 2025Feb 6, 2026May 28, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
89.31
87.1
86.88
2026.05
86.21
86.2
86.2
2026.05
86.2
2026.02
86
85.85
85.81
2026.05
85.57
85.45
2026.05
85.23
85
2026.05
84.34
2026.05
84.09
2026.05
83.97
2026.02
83.8
83.7
2026.02
83.7
83.6
83.52
83.46
2026.05
83.46
83.27
83.11
2026.05
83.11
83.02
2026.05
83.02
2026.05
82.95
2026.05
82.72
2026.05
82.65
2026.05
82.42
2026.05
82.02
81.74
2026.05
81.6
2026.05
81.31
81.02
80.95
80.9
2026.05
80.89
80.68
2026.05
80.62
2026.02
80.6
2026.02
80.6
2026.05
80.5
2026.05
79.68
2026.05
79.56
2026.05
79.46
2026.05
79.24
2026.05
79.22
2026.05
78.72
2026.05
78.5
2026.05
78.39
2026.05
78
2026.05
77.5
77.42
2026.05
77.2
2024.07
77
2026.05
77
2026.05
76.5
2026.01
76.1
2026.02
75.25
2026.05
75.02
2024.07
74
2026.05
73.94
2026.05
73.93
2026.05
73.84
73.47
2024.07
73.3
2026.05
73
2026.05
72.84
2026.05
72.78
2026.01
72.67
71.99
2026.05
71
2026.05
70.79
2026.05
70.24
2026.04
69.6
2026.05
69
2026.05
68.5
2026.05
68
67.84
2026.05
67.12
2026.04
66.76
2026.05
66.5
2026.05
66.5
2026.05
66.5
2024.07
66.4
2026.05
66.2
2026.01
66
2026.05
66
2026.02
65.15
2026.05
65
2026.05
64.9
2024.07
64.8
2026.05
64.5
2026.05
64.5
2026.05
64.5
2026.05
63.9
Showing 100 of 303 rows