---
title: intfloat/e5-small-v2
description: Text Embeddings by Weakly-Supervised Contrastive Pre-training. Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang,. BERT, 33M parameters.
canonical_url: https://superlinked.com/models/intfloat-e5-small-v2
last_updated: 2026-05-25
---

# intfloat/e5-small-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

Source: [intfloat/e5-small-v2 on HuggingFace](https://huggingface.co/intfloat/e5-small-v2)

## Overview

| Field | Value |
|-------|-------|
| Architecture | BERT |
| Parameters | 33M |
| Tasks | Encode |
| Outputs | Dense |
| Dimensions | Dense: 384 |
| Max sequence length | 512 tokens |
| License | mit |
| Inputs | text |
| Languages | en |

## Benchmarks

### CQADupstackPhysicsRetrieval

Domain: scientific · Task: retrieval · Language: en

Duplicate question retrieval from StackExchange Physics

Corpus: 38,314 · Queries: 1,039

**Performance (L4 b1 c16):** Corpus 42.5K tok/s · Corpus p50 47.8ms · Query 3.1K tok/s · Query p50 48.7ms

[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

**Performance (L4 b1 c16):** Corpus 16.7K tok/s · Corpus p50 49.7ms · Query 1.6K tok/s · Query p50 50.3ms

[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

**Performance (L4 b1 c16):** Corpus 41.5K tok/s · Corpus p50 57.8ms · Query 3.3K tok/s · Query p50 48.5ms

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

### LegalBenchConsumerContractsQA

Domain: legal · Task: retrieval · Language: en

Question answering on consumer contracts

Corpus: 153 · Queries: 396

**Performance (L4 b1 c16):** Corpus 115.7K tok/s · Corpus p50 63.0ms · Query 4.0K tok/s · Query p50 57.9ms

[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

**Performance (L4 b1 c16):** Corpus 95.9K tok/s · Corpus p50 45.8ms · Query 1.5K tok/s · Query p50 43.2ms

[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: 0.4299 · map at 10: 0.3531 · mrr at 10: 0.4611

**Performance (L4 b1 c16):** Corpus 58.3K tok/s · Corpus p50 40.3ms · Query 4.1K tok/s · Query p50 35.0ms

[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

**Performance (L4 b1 c16):** Corpus 57.1K tok/s · Corpus p50 49.9ms · Query 3.2K tok/s · Query p50 47.2ms

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

### SciFact

Domain: scientific · Task: retrieval · Language: en

Scientific claim verification using research literature

Corpus: 5,183 · Queries: 300

**Performance (L4 b1 c16):** Corpus 85.1K tok/s · Corpus p50 47.6ms · Query 4.6K tok/s · Query p50 48.1ms

[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

**Performance (L4 b1 c16):** Corpus 63.0K tok/s · Corpus p50 53.7ms · Query 55.0K tok/s · Query p50 75.1ms

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