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

General Knowledge and Reasoning on MMLU

89.5Accuracy

Claude Sonnet 4.5

43.625655.535367.44579.3547Aug 25, 2025Sep 30, 2025Nov 5, 2025Dec 11, 2025Jan 16, 2026Feb 21, 2026Mar 29, 2026
Updated 5d ago

Evaluation Results

MethodLinks
2025.11
89.5
89.28
2025.11
87.7
87.1
2025.11
86
83.95
79.91
2026.03
76.9
2026.03
76.1
2026.03
75.7
2026.03
75.2
2026.03
72.2
2026.03
71.8
2026.03
70.7
2025.11
69.1
2026.03
68.4
2025.11
67.3
2026.03
67.2
2026.03
66.6
2026.03
65.9
2025.08
63.1
2025.08
62.44
2026.03
52.1
2025.08
45.39