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

Language Understanding on MMLU-Pro

80.6Accuracy

gpt-oss-120B

25.615239.890154.16568.4399Jul 15, 2024Oct 25, 2024Feb 4, 2025May 17, 2025Aug 27, 2025Dec 7, 2025Mar 20, 2026
Updated 26d ago

Evaluation Results

MethodLinks
2026.02
80.6
2026.02
80.41
2026.02
79.32
2026.02
79.19
2026.02
78.86
2026.02
78.71
2026.02
78.18
2026.02
78.03
2026.02
75.62
2026.02
75.56
2026.02
75.18
2026.02
75.04
2025.12
71.9
2024.07
61.6
2025.12
59.1
2025.12
56.9
2024.07
55.6
2026.03
54.19
2026.03
54.07
2024.07
53.8
2026.03
53.72
52.8
2026.02
52
2024.07
51.5
2026.03
51.4
49.5
49.4
2026.03
49.21
2025.12
49.2
2026.02
49
2024.07
48.3
2025.12
48.2
45.8
2025.12
44.6
2024.07
44
2026.03
43.55
2025.12
43.3
2026.03
43.24
2024.07
43
2025.12
41.8
2026.02
41.67
41.67
2025.12
41.41
2024.07
41
2025.12
40.49
2025.12
39.2
2026.03
37.87
2026.02
37.5
2026.02
37.5
2026.02
37.5
2024.07
37.1
2026.02
36.11
2025.05
36.1
2025.05
35.8
2025.05
35.2
2024.07
35.1
2026.02
34.72
2026.03
34.61
2026.02
34.05
2025.05
34
2026.02
33.95
2026.02
33.52
2026.03
33.34
2024.07
32.5
2026.02
30.56
2025.05
29.6
2025.05
29.5
2025.12
29.39
2025.12
29.29
2025.12
29.22
2025.12
29.11
2025.05
29.1
2025.12
29.01
2025.12
28.81
2025.12
28.77
2025.12
28.76
2025.12
28.72
2025.12
28.72
2025.12
28.67
2025.12
28.65
2025.12
28.62
2025.12
28.57
2025.12
28.54
2025.12
28.47
2025.12
28.18
2025.12
28.03
2025.12
27.73