intfloat/e5-large-v2
Text Embeddings by Weakly-Supervised Contrastive Pre-training. Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, Furu Wei, arXiv 2022
Benchmarks
CQADupstackPhysicsRetrieval
Duplicate question retrieval from StackExchange Physics
Corpus: 38,314 Queries: 1,039
Performance L4 b1 c16
Corpus TPS 26.5K
Corpus p50 74.3ms
Query TPS 2.7K
Query p50 53.9ms
CosQA
Code search with natural language queries
Corpus: 6,267 Queries: 500
Performance L4 b1 c16
Corpus TPS 13.9K
Corpus p50 60.1ms
Query TPS 1.4K
Query p50 57.6ms
FiQA2018
Financial opinion mining and question answering
Corpus: 57,599 Queries: 648
Performance L4 b1 c16
Corpus TPS 31.6K
Corpus p50 80.9ms
Query TPS 2.8K
Query p50 55.5ms
LegalBenchConsumerContractsQA
Question answering on consumer contracts
Corpus: 153 Queries: 396
Performance L4 b1 c16
Corpus TPS 57.2K
Corpus p50 140.9ms
Query TPS 3.5K
Query p50 58.3ms
NFCorpus
Biomedical literature search from NutritionFacts.org
Corpus: 3,593 Queries: 323
Quality
ndcg at 10 0.3715
map at 10 0.1416
mrr at 10 0.5706
Performance L4 b1 c16
Corpus TPS 42.8K
Corpus p50 112.1ms
Query TPS 1.3K
Query p50 53.6ms
NanoFiQA2018Retrieval
Smaller subset of the FiQA financial QA dataset
Quality
ndcg at 10 0.4531
map at 10 0.3742
mrr at 10 0.5054
Performance L4 b1 c16
Corpus TPS 27.3K
Corpus p50 86.6ms
Query TPS 2.8K
Query p50 49.5ms
SCIDOCS
Citation prediction, document classification, and recommendation for scientific papers
Corpus: 25,656 Queries: 1,000
Performance L4 b1 c16
Corpus TPS 33.2K
Corpus p50 86.0ms
Query TPS 2.7K
Query p50 56.2ms
SciFact
Scientific claim verification using research literature
Corpus: 5,183 Queries: 300
Performance L4 b1 c16
Corpus TPS 39.4K
Corpus p50 108.1ms
Query TPS 3.6K
Query p50 58.1ms
StackOverflowQA
Programming question answering from Stack Overflow
Corpus: 19,931 Queries: 1,994
Performance L4 b1 c16
Corpus TPS 39.2K
Corpus p50 95.0ms
Query TPS 42.1K
Query p50 107.3ms