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

Model Merging on Sustainability to large-scale tasks

91.4Average Normalized Accuracy

DOGE AM

51.8862.1472.482.66Aug 5, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.08
91.4
2025.08
90.7
2025.08
90.4
2025.08
90
2025.08
89.7
2025.08
89.4
2025.08
88.7
2025.08
88.3
2025.08
87.3
2025.08
87.1
2025.08
86.9
2025.08
86.7
2025.08
86.4
2025.08
84.4
2025.08
81.4
2025.08
79.8
2025.08
78.2
2025.08
76.6
2025.08
75.3
2025.08
73.8
2025.08
73
2025.08
71.9
2025.08
65.4
2025.08
53.4