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

Knowledge Evaluation on MMLU

82.03MMLU Accuracy

W16A16-Direct

18.454834.959951.46567.9701Feb 13, 2026Mar 3, 2026Mar 21, 2026Apr 8, 2026Apr 26, 2026May 14, 2026Jun 1, 2026
Updated 23h ago

Evaluation Results

MethodLinks
2026.04
82.030
2026.04
81.98-0.06
2026.04
79.91-2.12
2026.04
79.78-2.25
2026.04
79.28-2.75
2026.04
78.93-3.1
2026.04
78.23-3.8
2026.04
74.970
2026.04
74.61-0.36
2026.02
74.26-
2026.02
73.65-
2026.06
73.51-
2026.02
73.41-
2026.02
73.31-
2026.04
72.64-2.33
2026.04
72.4-2.56
2026.04
72.26-2.71
2026.06
72.18-
2026.06
72.08-
2026.04
70.31-4.66
2026.06
68.79-
2026.04
68.24-6.73
2026.06
66.65-
2026.02
65.52-
2026.02
64.64-
2026.02
64.48-
2026.02
64.37-
2026.06
61.84-
2026.06
61.07-
2026.05
58.9-
2026.05
58.90
2026.05
58.90
2026.05
58.90
2026.05
58.90
2026.05
58.7-0.3
2026.05
58.6-0.5
2026.02
53.03-
2026.02
51.77-
2026.06
51.32-
2026.06
51.05-
2026.06
50.9-
2026.02
50.69-
2026.02
50.21-
2026.05
47.11-
2026.05
46.96-
2026.05
46.7-
2026.05
46.70
2026.05
46.70
2026.05
46.70
2026.05
46.70
2026.05
45.9-1.7
45.49-
45.22-
44.78-
2026.05
44.5-4.7
42.65-
2026.05
42.49-
2026.05
40.17-
2026.05
39.28-
2026.05
38.87-
2026.05
27.9-40.2
2026.05
23.63-
2026.05
22.49-
2026.05
20.9-64.5