---
title: opensearch-project/opensearch-neural-sparse-encoding-doc-v3-gte
description: "The model should be selected considering search relevance, model inference and retrieval efficiency(FLOPS). We benchmark models' performance. ModernBERT, 137M parameters."
canonical_url: https://superlinked.com/models/opensearch-project-opensearch-neural-sparse-encoding-doc-v3-gte
last_updated: 2026-05-25
---

# opensearch-project/opensearch-neural-sparse-encoding-doc-v3-gte

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.

Source: [opensearch-project/opensearch-neural-sparse-encoding-doc-v3-gte on HuggingFace](https://huggingface.co/opensearch-project/opensearch-neural-sparse-encoding-doc-v3-gte)

## Overview

| Field | Value |
|-------|-------|
| Architecture | ModernBERT |
| Parameters | 137M |
| Tasks | Encode |
| Outputs | Sparse |
| Dimensions | Sparse: 30,522 |
| Max sequence length | 512 tokens |
| License | apache-2.0 |
| Inputs | text |
| Languages | en |

## Benchmarks

### CQADupstackPhysicsRetrieval

Domain: scientific · Task: retrieval · Language: en

Duplicate question retrieval from StackExchange Physics

Corpus: 38,314 · Queries: 1,039

**Quality:** ndcg at 10: 0.4057 · map at 10: 0.3518 · mrr at 10: 0.4049

**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](http://nlp.cis.unimelb.edu.au/resources/cqadupstack/)

### CosQA

Domain: technology · Task: retrieval · Language: en

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](https://arxiv.org/abs/2105.13239)

### FiQA2018

Domain: finance · Task: retrieval · Language: en

Financial opinion mining and question answering

Corpus: 57,599 · Queries: 648

**Quality:** ndcg at 10: 0.4062 · map at 10: 0.3301 · mrr at 10: 0.4849

**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](https://sites.google.com/view/fiqa/)

### LegalBenchConsumerContractsQA

Domain: legal · Task: retrieval · Language: en

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](https://huggingface.co/datasets/nguha/legalbench)

### NFCorpus

Domain: medical · Task: retrieval · Language: en

Biomedical literature search from NutritionFacts.org

Corpus: 3,593 · Queries: 323

**Quality:** ndcg at 10: 0.3606 · map at 10: 0.1391 · mrr at 10: 0.5725

**Performance (L4 b1 c16):** Corpus 37.7K tok/s · Corpus p50 114.2ms · Query 1.7K tok/s · Query p50 43.9ms

[Reference](https://www.cl.uni-heidelberg.de/statnlpgroup/nfcorpus/)

### SCIDOCS

Domain: scientific · Task: retrieval · Language: en

Citation prediction, document classification, and recommendation for scientific papers

Corpus: 25,656 · Queries: 1,000

**Quality:** ndcg at 10: 0.1586 · map at 10: 0.0918 · mrr at 10: 0.2747

**Performance (L4 b1 c16):** Corpus 34.2K tok/s · Corpus p50 86.0ms · Query 4.2K tok/s · Query p50 41.2ms

[Reference](https://allenai.org/data/scidocs)

### SciFact

Domain: scientific · Task: retrieval · Language: en

Scientific claim verification using research literature

Corpus: 5,183 · Queries: 300

**Quality:** ndcg at 10: 0.6262 · map at 10: 0.5830 · mrr at 10: 0.5966

**Performance (L4 b1 c16):** Corpus 40.0K tok/s · Corpus p50 103.7ms · Query 5.9K tok/s · Query p50 43.4ms

[Reference](https://github.com/allenai/scifact)

### StackOverflowQA

Domain: technology · Task: retrieval · Language: en

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](https://arxiv.org/abs/2407.02883)