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

Multi-task learning evaluation on MM-MergeBench 8 tasks 1.0 (test)

92.83Avg Absolute Accuracy

Individual

46.477258.511170.54582.5789Mar 6, 2026
Updated 4mo ago

Evaluation Results

MethodLinks
2026.03
92.83-
2026.03
87.0593.55
2026.03
86.4793.05
2026.03
86.291.78
2026.03
85.8692.31
2026.03
48.26-