---
title: Snowflake/snowflake-arctic-embed-s
description: "Snowflake's Arctic-embed-s. BERT, 33M parameters."
canonical_url: https://superlinked.com/models/snowflake-snowflake-arctic-embed-s
last_updated: 2026-08-24
---

# Snowflake/snowflake-arctic-embed-s

Snowflake's Arctic-embed-s

Source: [Snowflake/snowflake-arctic-embed-s on HuggingFace](https://huggingface.co/Snowflake/snowflake-arctic-embed-s)

## Overview

| Field | Value |
|-------|-------|
| Architecture | BERT |
| Parameters | 33M |
| Tasks | Encode |
| Outputs | Dense |
| Dimensions | Dense: 384 |
| Max sequence length | 512 tokens |
| License | apache-2.0 |
| Inputs | text |

## Benchmarks

### CQADupstackPhysicsRetrieval

Domain: scientific · Task: retrieval · Language: en

Duplicate question retrieval from StackExchange Physics

Corpus: 38,314 · Queries: 1,039

**Quality:** ndcg at 10: 0.4629 · map at 10: 0.4070 · mrr at 10: 0.4648

**Performance (L4 b1 c16):** Corpus 66.0K tok/s · Corpus p50 25.4ms · Query 5.6K tok/s · Query p50 25.0ms

[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: 0.3384 · map at 10: 0.2721 · mrr at 10: 0.2891

**Performance (L4 b1 c16):** Corpus 24.9K tok/s · Corpus p50 25.6ms · Query 3.1K tok/s · Query p50 25.6ms

[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: 0.3972 · map at 10: 0.3178 · mrr at 10: 0.4702

**Performance (L4 b1 c16):** Corpus 78.9K tok/s · Corpus p50 27.2ms · Query 6.1K tok/s · Query p50 24.5ms

[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: 0.7474 · map at 10: 0.6905 · mrr at 10: 0.6913

**Performance (L4 b1 c16):** Corpus 172.1K tok/s · Corpus p50 29.8ms · Query 8.6K tok/s · Query p50 24.8ms

[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: 0.3265 · map at 10: 0.1209 · mrr at 10: 0.5400

**Performance (L4 b1 c16):** Corpus 135.2K tok/s · Corpus p50 28.9ms · Query 2.6K tok/s · Query p50 25.4ms

[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: 0.1941 · map at 10: 0.1165 · mrr at 10: 0.3400

**Performance (L4 b1 c16):** Corpus 92.0K tok/s · Corpus p50 26.4ms · Query 5.8K tok/s · Query p50 25.5ms

[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: 0.6985 · map at 10: 0.6540 · mrr at 10: 0.6683

**Performance (L4 b1 c16):** Corpus 125.3K tok/s · Corpus p50 27.4ms · Query 8.5K tok/s · Query p50 25.4ms

[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: 0.8303 · map at 10: 0.8014 · mrr at 10: 0.8014

**Performance (L4 b1 c16):** Corpus 106.1K tok/s · Corpus p50 27.6ms · Query 131.6K tok/s · Query p50 28.5ms

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