---
title: Salesforce/SFR-Embedding-2_R
description: Salesforce/SFR-Embedding-2_R. Mistral, 7.1B parameters.
canonical_url: https://superlinked.com/models/salesforce-sfr-embedding-2_r
last_updated: 2026-09-05
---

# Salesforce/SFR-Embedding-2_R

Salesforce/SFR-Embedding-2_R

Source: [Salesforce/SFR-Embedding-2_R on HuggingFace](https://huggingface.co/Salesforce/SFR-Embedding-2_R)

## Overview

| Field | Value |
|-------|-------|
| Architecture | Mistral |
| Parameters | 7.1B |
| Tasks | Encode |
| Outputs | Dense |
| Dimensions | Dense: 4,096 |
| Max sequence length | 32,768 tokens |
| License | cc-by-nc-4.0 |
| 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: 0.5257 · map at 10: 0.4585 · mrr at 10: 0.5103

[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: 0.2965 · map at 10: 0.2287 · mrr at 10: 0.2319

[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: 0.6204 · map at 10: 0.5384 · mrr at 10: 0.6880

[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: 0.7830 · map at 10: 0.7269 · mrr at 10: 0.7269

[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: 0.4142 · map at 10: 0.1587 · mrr at 10: 0.6177

**Performance (L4 b1 c16):** Corpus 3.0K tok/s · Corpus p50 1.0s · Query 210 tok/s · Query p50 260.3ms

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

### NanoFiQA2018Retrieval

Domain: finance · Task: retrieval · Language: en

Smaller subset of the FiQA financial QA dataset

**Quality:** ndcg at 10: 0.6468 · map at 10: 0.5714 · mrr at 10: 0.6532

**Performance (L4 b1 c16):** Corpus 2.9K tok/s · Corpus p50 682.5ms · Query 457 tok/s · Query p50 238.4ms

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

### 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: 0.2488 · map at 10: 0.1515 · mrr at 10: 0.4078

[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: 0.8564 · map at 10: 0.8177 · mrr at 10: 0.8270

[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: 0.9407 · map at 10: 0.9289 · mrr at 10: 0.9289

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