Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Poli

Benchmarks

Task NameDataset NameSOTA ResultTrend
Unsupervised Feature SelectionPoli
NMI54.71
14
ClusteringPoli
Accuracy58.02
14
Sycophancy EvaluationPOLI
Sycophantic Preference (%)92.18
10
Showing 3 of 3 rows