---
title: lightonai/mLateOn (Encode)
description: State-of-the-Art Multilingual ColBERT Retrieval Model by LightOn. ModernBERT, 307M parameters.
canonical_url: https://superlinked.com/models/lightonai-mlateon--encode
last_updated: 2026-08-24
---

# lightonai/mLateOn (Encode)

State-of-the-Art Multilingual ColBERT Retrieval Model by LightOn

Source: [lightonai/mLateOn on HuggingFace](https://huggingface.co/lightonai/mLateOn)
Base model: [lightonai/mLateOn-unsupervised](https://huggingface.co/lightonai/mLateOn-unsupervised)

## Overview

| Field | Value |
|-------|-------|
| Architecture | ModernBERT |
| Parameters | 307M |
| Tasks | Encode, Score |
| Outputs | Multi-Vec |
| Dimensions | Multi-Vec: 128 |
| Max sequence length | 8,192 tokens |
| License | apache-2.0 |
| Inputs | text |
| Languages | en, fr, de, it, es, pt, sv, no, ar, code |

## Benchmarks

### CQADupstackPhysicsRetrieval

Domain: scientific · Task: retrieval · Language: en

Duplicate question retrieval from StackExchange Physics

Corpus: 38,314 · Queries: 1,039

**Quality:** ndcg at 10: 0.4723 · map at 10: 0.4116 · mrr at 10: 0.4703

[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: 0.3916 · map at 10: 0.2995 · mrr at 10: 0.2784

[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: 0.4991 · map at 10: 0.4143 · mrr at 10: 0.5711

[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: 0.8567 · map at 10: 0.8173 · mrr at 10: 0.8181

[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: 0.3776 · map at 10: 0.1479 · mrr at 10: 0.5900

[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: 0.2047 · map at 10: 0.1233 · mrr at 10: 0.3506

[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: 0.7646 · map at 10: 0.7261 · mrr at 10: 0.7369

[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: 0.9239 · map at 10: 0.9105 · mrr at 10: 0.9105

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