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

Multi-task Language Understanding on MMLU Biz

90F1 Score

SharedRequest (Original)

36.02450.03764.0578.063Jun 3, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
90
2026.06
89.9
2026.06
85.3
2026.06
85.1
2026.06
84.8
2026.06
84.8
2026.06
81.7
2026.06
81.7
2026.06
76.3
2026.06
75.8
2026.06
75.8
2026.06
75.4
2026.06
74.6
2026.06
74.3
2026.06
71.2
2026.06
70.8
2026.06
70
2026.06
69.5
2026.06
69.4
2026.06
68.6
2026.06
67.1
2026.06
66.5
2026.06
64.9
2026.06
63.8
2026.06
63.1
2026.06
60.3
2026.06
55.3
2026.06
54.2
2026.06
53.3
2026.06
52.9
2026.06
52.2
2026.06
51.1
2026.06
49.7
2026.06
49.6
2026.06
47.3
2026.06
43.5
2026.06
41.1
2026.06
40.5
2026.06
39
2026.06
38.8
2026.06
38.1