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

Knowledge on MMLU-Redux (test)

69.8Knowledge Accuracy

ReM-MoA*

21.887234.326146.76559.2039Jun 13, 2025Aug 14, 2025Oct 16, 2025Dec 17, 2025Feb 18, 2026Apr 21, 2026Jun 23, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
69.8
2026.06
69.5
2026.06
69.3
2026.06
69.2
2026.06
69
2026.06
68.8
2026.06
68.7
2026.06
68.3
2026.06
68.2
2026.06
67.8
2026.06
67.4
2026.06
67
2026.06
65.5
2026.06
65.5
2026.06
65.4
2026.06
65.4
2026.06
65.3
2026.06
65.2
2026.06
65.2
2026.06
65.2
2026.06
65.1
2026.06
65.1
2026.06
65
2026.06
64.8
2026.06
58.2
2026.06
57.2
2026.06
56.5
2026.06
55.8
2026.06
55.2
2026.06
54.5
2025.06
30.93
2025.06
28.9
2025.06
23.73