intfloat/e5-base-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 40.2K
Corpus p50 48.6ms
Query TPS 3.0K
Query p50 45.9ms
CosQA
Code search with natural language queries
Corpus: 6,267 Queries: 500
Performance L4 b1 c16
Corpus TPS 18.8K
Corpus p50 43.2ms
Query TPS 1.9K
Query p50 43.0ms
FiQA2018
Financial opinion mining and question answering
Corpus: 57,599 Queries: 648
Performance L4 b1 c16
Corpus TPS 45.2K
Corpus p50 52.3ms
Query TPS 3.4K
Query p50 45.4ms
LegalBenchConsumerContractsQA
Question answering on consumer contracts
Corpus: 153 Queries: 396
Performance L4 b1 c16
Corpus TPS 109.6K
Corpus p50 68.3ms
Query TPS 5.1K
Query p50 45.0ms
NFCorpus
Biomedical literature search from NutritionFacts.org
Corpus: 3,593 Queries: 323
Quality
ndcg at 10 0.3541
map at 10 0.1311
mrr at 10 0.5549
Performance L4 b1 c16
Corpus TPS 79.2K
Corpus p50 57.9ms
Query TPS 1.5K
Query p50 42.8ms
NanoFiQA2018Retrieval
Smaller subset of the FiQA financial QA dataset
Quality
ndcg at 10 0.4603
map at 10 0.3791
mrr at 10 0.5059
Performance L4 b1 c16
Corpus TPS 33.6K
Corpus p50 63.5ms
Query TPS 3.5K
Query p50 49.2ms
SCIDOCS
Citation prediction, document classification, and recommendation for scientific papers
Corpus: 25,656 Queries: 1,000
Performance L4 b1 c16
Corpus TPS 53.2K
Corpus p50 53.2ms
Query TPS 3.4K
Query p50 45.6ms
SciFact
Scientific claim verification using research literature
Corpus: 5,183 Queries: 300
Performance L4 b1 c16
Corpus TPS 67.5K
Corpus p50 59.2ms
Query TPS 4.6K
Query p50 47.7ms
StackOverflowQA
Programming question answering from Stack Overflow
Corpus: 19,931 Queries: 1,994
Performance L4 b1 c16
Corpus TPS 55.7K
Corpus p50 59.0ms
Query TPS 63.4K
Query p50 63.1ms