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

ConvAI

Benchmarks

Task NameDataset NameSOTA ResultTrend
Dialogue Response GenerationConvAI2
F122.89
12
ASR RescoringConvAI (test)
WER5.07
11
Red Teaming against BB-3BConvAI2
RSR45
9
Dialogue EvaluationConvAI2
Pearson Correlation0.554
9
Showing 4 of 4 rows