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

VP

Benchmarks

Task NameDataset NameSOTA ResultTrend
Code Correctness EvaluationVP
F1 Score66
24
Upright blockVP2
Mean Success Rate90
7
ClassificationVP UCI (test)
Accuracy97.59
6
ClassificationVP (UCI) (train)
Accuracy97.8
6
Showing 4 of 4 rows