← Catalog
opensearch-project/opensearch-neural-sparse-encoding-doc-v3-gte Add to compare Open comparison →
Primitive: /encode · Encode ·
ModernBERT
The model should be selected considering search relevance, model inference and retrieval efficiency(FLOPS). We benchmark models' performance on a subset of BEIR benchmark: TrecCovid,NFCorpus,NQ,HotpotQA,FiQA,ArguAna,Touche,DBPedia,SCIDOCS,FEVER,Climate FEVER,SciFact,Quora.
Sparse
View on Hugging Face →
Overview
Hardware:
L4 RTX-PRO-6000 — drives latency, throughput & cost
Size 137M params Tasks /encode License apache-2.0 Languages en Latency 94 ms Throughput 34.2K tok/s Cost $0.0065 /1M tok
Cost is approximate — computed from list GPU prices; your actual price depends on the provider you deploy SIE with.
Embedding Output types Sparse Dimensions sparse: 30,522 Max sequence length 512 Inputs text
Benchmarks Duplicate question retrieval from StackExchange Physics
Corpus: 38,314 Queries: 1,039
Quality
map at 10 0.3518
mrr at 10 0.4048
ndcg at 10 0.4056
Performance A10G b1 c16
Corpus 1 tok/s
Corpus p50 4.0s
Query 0 tok/s
Query p50 32.5s
Performance L4 b1 c16
Corpus 24.3K tok/s
Corpus p50 75.0ms
Query 4.2K tok/s
Query p50 40.6ms
Reference →
Code search with natural language queries
Corpus: 6,267 Queries: 500
Quality
ndcg at 10 0.2244
map at 10 0.1739
mrr at 10 0.1860
Performance A10G b1 c16
Corpus 24 tok/s
Corpus p50 42.5s
Query 24 tok/s
Query p50 3.6s
Performance L4 b1 c16
Corpus 12.4K tok/s
Corpus p50 61.4ms
Query 2.1K tok/s
Query p50 43.2ms
Reference →
Financial opinion mining and question answering
Corpus: 57,599 Queries: 648
Quality
map at 10 0.2771
mrr at 10 0.4170
ndcg at 10 0.3507
Performance A10G b1 c16
Corpus 0 tok/s
Corpus p50 2.0s
Query 0 tok/s
Query p50 0.0ms
Performance L4 b1 c16
Corpus 29.2K tok/s
Corpus p50 78.9ms
Query 4.4K tok/s
Query p50 40.6ms
Reference →
Question answering on consumer contracts
Corpus: 153 Queries: 396
Quality
ndcg at 10 0.7290
map at 10 0.6704
mrr at 10 0.6712
Performance L4 b1 c16
Corpus 59.1K tok/s
Corpus p50 127.0ms
Query 6.2K tok/s
Query p50 41.7ms
Reference →
Biomedical literature search from NutritionFacts.org
Corpus: 3,593 Queries: 323
Performance L4 b1 c16
Corpus 37.7K tok/s
Corpus p50 114.2ms
Query 1.7K tok/s
Query p50 43.9ms
Reference →
Citation prediction, document classification, and recommendation for scientific papers
Corpus: 25,656 Queries: 1,000
Quality
map at 10 0.0820
mrr at 10 0.2523
ndcg at 10 0.1419
Performance L4 b1 c16
Corpus 34.2K tok/s
Corpus p50 86.0ms
Query 4.2K tok/s
Query p50 41.2ms
Reference →
Scientific claim verification using research literature
Corpus: 5,183 Queries: 300
Quality
map at 10 0.6829
mrr at 10 0.6972
ndcg at 10 0.7243
Performance L4 b1 c16
Corpus 40.0K tok/s
Corpus p50 103.7ms
Query 5.9K tok/s
Query p50 43.4ms
Reference →
Programming question answering from Stack Overflow
Corpus: 19,931 Queries: 1,994
Quality
ndcg at 10 0.7470
map at 10 0.7160
mrr at 10 0.7160
Performance L4 b1 c16
Corpus 34.1K tok/s
Corpus p50 101.3ms
Query 78.1K tok/s
Query p50 57.0ms
Reference →
