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

SEARCH

Benchmarks

Task NameDataset NameSOTA ResultTrend
Agentic SearchSearch Unseen
PopQA Accuracy52.3
19
Agentic SearchSearch Seen
NQ Accuracy51.6
19
CTR PredictionSearch (test)
AUC0.8219
10
RecommendationSearch
HR@10.0086
8
Search PersonalizationSEARCH 17 (test)
MRR76.6
7
Feasibility PredictionSearch R1
F1@140.2
5
RecommendationSearch
P-value0.021
1
Showing 7 of 7 rows