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

BEIR

Benchmarks

Task NameDataset NameSOTA ResultTrend
Information RetrievalBEIR (test)
FiQA-2018 Score65.6
90
Information RetrievalBEIR v1.0.0 (test)
ArguAna72.9
65
Information RetrievalBEIR
Average NDCG@100.635
62
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
Information RetrievalBEIR COVID v1 (test)
nDCG@1063.5
26
Document RerankingBEIR
NDCG@10 (Covid)85.51
24
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
Document RerankingBEIR
Average NDCG@1055.4
17
Semantic RelatednessBEIR Semantic Relatedness Tasks (test)
ArguAna Score47.9
16
Re-rankingBEIR OOD
Ar Score41
15
Text RetrievalBEIR-5 all-MiniLM-L6-v2 (test)
Average NDCG@1052.3
14
Document RerankingBEIR
SF80.87
13
Information RetrievalBEIR top-60
TREC-COVID Score77.9
13
RetrievalBEIR
nDCG@1 (NFC)0.36
13
Dense RetrievalBEIR zero-shot
TREC-COVID77.2
13
Document RerankingBEIR
Average NDCG@1055.1
12
Passage RerankingBEIR (test)
Covid85.99
11
Information RetrievalBEIR v1.0 (test)
ARCD Score98.9
10
Text RankingBEIR out-of-domain
Arguana Score55.6
9
Passage RerankingBEIR
FiQA Score44.3
8
Showing 25 of 39 rows