Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

BEIR

Benchmarks

Task NameDataset NameSOTA ResultTrend
Information RetrievalBEIR (test)
TREC-COVID Score75.7
76
Information RetrievalBEIR
TREC-COVID0.873
59
Information RetrievalBEIR v1.0.0 (test)
ArguAna72.68
55
RankingBEIR selected subset v1.0.0 (test)
TREC-COVID84.7
38
RerankingBEIR
NQ NDCG@50.5106
35
Zero-shot Information RetrievalBEIR
Trec-Covid NDCG@10 (Zero-shot)78.9
27
Re-rankingBEIR (test)
NQ59.3
23
Information RetrievalBEIR v1 (test)
ArguAna49.2
22
Document RetrievalBEIR 15
NDCG@100.443
21
OOD document detectionBEIR (test)
ArguAna1
20
Re-rankingBEIR OOD
Ar Score41
15
Text RetrievalBEIR-5 all-MiniLM-L6-v2 (test)
Average NDCG@1052.3
14
Document RerankingBEIR
NDCG@10 (Covid)87.6
13
RetrievalBEIR
nDCG@1 (NFC)0.36
13
Dense RetrievalBEIR zero-shot
TREC-COVID77.2
13
Passage RerankingBEIR (test)
Covid85.99
11
Document RerankingBEIR
NDCG@10 (Covid)81.08
10
Information RetrievalBEIR v1.0 (test)
ARCD Score98.9
10
Text RankingBEIR out-of-domain
Arguana Score55.6
9
Semantic RelatednessBEIR Semantic Relatedness Tasks (test)
ArguAna Score47.9
8
RerankingNanoBEIR
NDCG@1071.58
8
Information RetrievalBEIR unseen 8 subsets (test)
nDCG@1048.16
7
Relevance LabelingBEIR RobustQA
Class-wise Recall (Irrelevance)94.1
7
Information RetrievalBEIR BM25 Top-100 initial retrieval
TREC-COVID Score84.7
7
Information RetrievalBEIR Average of ArguAna, Quora, and Scidocs
nDCG67
6
Showing 25 of 31 rows