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

Eval-Actions

Benchmarks

Task NameDataset NameSOTA ResultTrend
Source PredictionEval-Actions 1.0 (test)
Accuracy99.6
17
Success PredictionEval-Actions 1.0 (test)
Accuracy91
17
Score PredictionEval-Actions 1.0 (test)
SRCC0.84
17
Showing 3 of 3 rows