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

StackOverflow

Benchmarks

Task NameDataset NameSOTA ResultTrend
Open intent recognitionStackOverflow
Accuracy88.98
54
Event PredictionStackOverFlow
RMSE0.464
42
Short Text ClusteringStackOverflow
Accuracy83.3
38
Marked Temporal Point ProcessStackOverflow (test)
RMSE0.948
20
RerankingStackOverflow (test)
MAP40.92
16
ClusteringStackOverflow (test)
ARI52.59
14
ClusteringStackOverflow
NMI78.8
13
Document RetrievalStackOverflow (test)
Precision@559.2
11
Topic ModelingStackOverflow
Cv0.397
11
Unknown Intent DetectionStackOverflow 50% seen classes (test)
Accuracy86.4
11
Next Word PredictionStackoverflow (test)
Generalized Accuracy (Accg)26.64
9
New Intent DiscoveryStackOverflow
NMI78.71
8
ClassificationStackoverflow (test)
Accp > Accg Percentage92.74
8
Event Time PredictionStackOverflow
RMSE1.12
7
Unknown Intent DetectionStackOverflow 75% seen classes (test)
Accuracy81.71
6
Unknown Intent DetectionStackOverflow 25% seen classes (test)
Accuracy68.74
6
Open Intent ClassificationStackOverflow 75% known classes (test)
Accuracy82.78
5
Open Intent ClassificationStackOverflow 25% known classes (test)
Accuracy86.72
5
Data TransformationStackOverflow
Accuracy65.3
3
SQL-to-text generationStackoverflow
BLEU-423.3
3
Showing 20 of 20 rows