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

Classification tasks

Benchmarks

Task NameDataset NameSOTA ResultTrend
Classification9 classification tasks (test)
Accuracy53.8
24
Classification50 classification tasks (test)
Average Test Rank1.38
19
Classification6 classification tasks few-shot
Accuracy64.8
10
Zero-shot Classification7 Classification Tasks
Mean Performance53.88
7
Text ClassificationClassification tasks
ARG Success Rate (Cls -> Cls)20.16
5
Classification18 Classification tasks aggregated
Accuracy82
4
Showing 6 of 6 rows