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

Language Understanding on MMLU (MMLU Score)

73.02MMLU Score

BF16 Baseline

20.947234.466147.98561.5039Dec 10, 2024Jan 29, 2025Mar 20, 2025May 9, 2025Jun 28, 2025Aug 17, 2025Oct 6, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.07
73.02
2024.12
73.01
2025.07
72.63
2025.07
72.28
2025.07
72.27
2025.07
72.23
2024.12
72.18
2025.07
72.15
2025.07
72.12
2024.12
71.94
2025.07
71.89
2024.12
71.82
2024.12
71.78
2025.07
71.76
2024.12
71.51
2025.07
70.96
2025.07
70.76
2024.12
70.73
2024.12
70.43
2025.07
69.88
2025.07
69.71
2025.07
69.66
2025.07
69.51
2025.07
68.46
2024.12
68.23
2025.07
67.85
2024.12
67.16
2025.07
65.8
2025.04
65.43
2025.04
65.33
2025.04
65.32
2025.04
65.3
2025.04
65.25
2025.04
65.22
2025.04
65.18
2025.04
63.19
2025.07
58.67
2025.10
56.1
2025.10
56
2025.10
55.7
2025.04
54.64
2025.07
54.07
2025.10
53.4
2025.07
52.99
2025.04
52.86
2025.04
52.76
2025.04
52.66
2025.04
52.3
2025.04
51.9
2025.04
51.66
2025.04
50.11
2025.07
49.6
2025.07
49.53
2025.07
49.32
2025.07
48.64
2025.10
48.5
2025.10
48.2
2025.07
47.9
2025.10
47.8
2025.10
47.7
2025.10
47.7
2025.10
47.6
2025.10
47.3
2025.07
47.04
2025.10
46.9
2025.10
46.9
2025.10
46.9
2025.10
46.8
2025.10
46.7
2025.07
46.22
2025.07
45.77
2025.07
45.39
2025.07
44.85
2025.04
38.14
2025.07
38.1
2025.07
37.76
2025.07
37.48
2025.04
37.35
2025.07
37.27
2025.04
37.2
2025.07
36.99
2025.04
36.89
2025.04
36.58
2025.04
35.94
2025.04
35.91
2025.04
35.53
2025.07
34.25
2025.07
33.91
2025.07
33.37
2025.07
33.37
2025.07
31.53
2025.07
30.35
2025.07
28.99
2025.07
28.8
2025.07
28.58
2025.07
27.89
2025.07
26.71
2025.07
22.95