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

Language Understanding on MMLU (Acc, Peak, Dep)

66.5Accuracy (MMLU)

CoT

51.10855.10459.163.096Apr 4, 2026
Updated 11d ago

Evaluation Results

MethodLinks
2026.04
66.56490.2
2026.04
65.827360.3
2026.04
60.271,1333
2026.04
59.822,1114.9
2026.04
59.721,3704.5
2026.04
59.591,3946.5
2026.04
57.681,1414.1
2026.04
57.582,4326.5
2026.04
57.062,4996.9
2026.04
54.42,8319.1
2026.04
53.465820.8
2026.04
51.72,4837.5