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

Octopus

Benchmarks

Task NameDataset NameSOTA ResultTrend
Tool SelectionOctopus v2 (test)
Recall@197.5
4
ClassificationOCTOPUS
Accuracy85.2
3
Gram matrix computationOctopus
Metric-
0
Showing 3 of 3 rows