---
title: NovaSearch/stella_en_400M_v5
description: We released a Jasper and Stella model technology report and code.(2025.1). ModernBERT, 435M parameters.
canonical_url: https://superlinked.com/models/novasearch-stella_en_400m_v5
last_updated: 2026-05-25
---

# NovaSearch/stella_en_400M_v5

We released a Jasper and Stella model technology report and code.(2025.1)

Source: [NovaSearch/stella_en_400M_v5 on HuggingFace](https://huggingface.co/NovaSearch/stella_en_400M_v5)

## Overview

| Field | Value |
|-------|-------|
| Architecture | ModernBERT |
| Parameters | 435M |
| Tasks | Encode |
| Outputs | Dense |
| Dimensions | Dense: 1,024 |
| Max sequence length | 512 tokens |
| License | mit |
| 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: 0.4836 · map at 10: 0.4156 · mrr at 10: 0.4717

**Performance (L4 b1 c16):** Corpus 24.3K tok/s · Corpus p50 84.2ms · Query 2.5K tok/s · Query p50 56.9ms

[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: 0.3216 · map at 10: 0.2529 · mrr at 10: 0.2719

**Performance (L4 b1 c16):** Corpus 12.8K tok/s · Corpus p50 67.0ms · Query 1.4K tok/s · Query p50 59.0ms

[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: 0.5589 · map at 10: 0.4742 · mrr at 10: 0.6391

**Performance (L4 b1 c16):** Corpus 24.7K tok/s · Corpus p50 97.7ms · Query 2.6K tok/s · Query p50 59.9ms

[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: 0.8107 · map at 10: 0.7633 · mrr at 10: 0.7645

**Performance (L4 b1 c16):** Corpus 39.7K tok/s · Corpus p50 209.7ms · Query 3.6K tok/s · Query p50 61.0ms

[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: 0.4125 · map at 10: 0.1615 · mrr at 10: 0.6096

**Performance (L4 b1 c16):** Corpus 30.3K tok/s · Corpus p50 164.6ms · Query 1.1K tok/s · Query p50 68.1ms

[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: 0.6158 · map at 10: 0.5412 · mrr at 10: 0.6537

**Performance (L4 b1 c16):** Corpus 25.2K tok/s · Corpus p50 103.9ms · Query 2.7K tok/s · Query p50 58.3ms

[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: 0.2501 · map at 10: 0.1523 · mrr at 10: 0.4130

**Performance (L4 b1 c16):** Corpus 27.1K tok/s · Corpus p50 115.7ms · Query 2.6K tok/s · Query p50 57.4ms

[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: 0.7842 · map at 10: 0.7358 · mrr at 10: 0.7455

**Performance (L4 b1 c16):** Corpus 28.4K tok/s · Corpus p50 156.1ms · Query 3.4K tok/s · Query p50 60.0ms

[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: 0.8666 · map at 10: 0.8439 · mrr at 10: 0.8439

**Performance (L4 b1 c16):** Corpus 28.2K tok/s · Corpus p50 134.6ms · Query 31.9K tok/s · Query p50 153.3ms

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