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

SB

Benchmarks

Task NameDataset NameSOTA ResultTrend
ClusteringSB
Clustering Accuracy97.23
23
ClusteringSB
ARI0.9562
23
Jailbreak Defense EvaluationSB
Strong-Reject Score (SR)3.258
21
Jailbreak DetectionSB
COR98.33
13
Static Schrödinger Bridge ApproximationSB Benchmark
$BW^2_2$-UVP (ε=0.1, D=2) Error1.6
8
Tabular ClassificationSB
Macro F195.7
6
ClassificationSB
Accuracy94.8
1
Showing 7 of 7 rows