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

General Knowledge on MMLU (test)

87.6Accuracy

SC-MAS

25.657641.738857.8273.9012Jul 20, 2025Aug 22, 2025Sep 24, 2025Oct 28, 2025Nov 30, 2025Jan 2, 2026Feb 5, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
87.6
2026.01
84.25
2026.01
83.22
2026.01
83.1
2026.01
83.1
2026.01
83.02
2026.01
82.8
2026.01
82.35
2026.01
82.01
2026.01
81.04
2026.01
80.04
2026.01
79.08
2026.01
78.43
2026.01
77.81
2026.01
76.24
2026.01
73.9
2026.01
68.4
2026.01
67.97
2026.01
65.5
2026.02
54.9
2026.02
54.7
2026.02
54.2
2026.02
53.9
2026.02
53
2025.07
52.11
2026.02
52
2026.02
51.9
2025.07
51.56
2025.07
50.73
2026.02
49.4
2026.01
49.4
2025.07
48.63
2026.02
47.1
2026.02
46.4
2026.02
46.3
2026.02
46
2025.07
45.55
2025.07
44.99
2025.07
44.51
2026.02
43.9
2025.07
43.55
2025.07
38.38
2025.07
38.23
2025.07
38.06
2025.07
37.88
2025.07
34.53
2025.07
33.97
2025.07
33.71
2025.07
33.29
2025.07
28.36
2025.07
28.32
2025.07
28.09
2025.07
28.04