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

Google

Benchmarks

Task NameDataset NameSOTA ResultTrend
Analogy recognitionGoogle
Accuracy99.41
15
Explainable RecommendationGoogle
BLEU0.3922
13
Analogy GenerationGoogle
Accuracy100
11
Sentence CompressionGoogle
F1 Score82
7
Early predictionGoogle-13
Accuracy0.9243
6
Wide-angle portrait correctiongoogle (test)
Line Accuracy66.098
5
Sentence CompressionGoogle (test)
Read Score3.94
5
Material ClassificationGoogle (test)
Accuracy92
4
Showing 8 of 8 rows