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

Retrieval Quality Evaluation

Benchmarks

Task NameDataset NameSOTA ResultTrend
Overall Retrieval (Average)Retrieval Quality Evaluation (test)
Recall92.9
8
Creative GenerationRetrieval Quality Evaluation (test)
Recall94.81
8
Contextual UnderstandingRetrieval Quality Evaluation (test)
Recall94.66
8
Complex ReasoningRetrieval Quality Evaluation (test)
Recall91.89
8
Fact RetrievalRetrieval Quality Evaluation (test)
Recall90.25
8
Showing 5 of 5 rows