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

Sustainability to large-scale tasks

Benchmarks

Task NameDataset NameSOTA ResultTrend
Model MergingSustainability to large-scale tasks
Average Normalized Accuracy91.4
24
Model MergingSustainability to large-scale tasks 2 tasks
Average Normalized Accuracy101.2
24
Model MergingSustainability to large-scale tasks (20 tasks)
Average Normalized Accuracy82.9
12
Model MergingSustainability to large-scale tasks 4 tasks
Average Accuracy98.3
12
Showing 4 of 4 rows