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

Multiple-choice Question Answering on MMLU-Pro (General Accuracy)

81.5Accuracy (MMLU-Pro)

ARMOR-MAD

52.3859.9467.575.06Jun 8, 2026Jun 9, 2026Jun 10, 2026Jun 11, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
81.5
2026.06
79
2026.06
76
2026.06
71.5
2026.06
66.2
2026.06
66
2026.06
65
2026.06
63.2
2026.06
62.32
2026.06
61.82
2026.06
61.5
2026.06
59.91
2026.06
54
2026.06
53.5