---
title: lightonai/Reason-ModernColBERT (Score)
description: Reason-ModernColBERT is a late interaction model trained on the reasonir-hq dataset. It achieves extremely competitive performance on the BR. ModernBERT, 149M parameters.
canonical_url: https://superlinked.com/models/lightonai-reason-moderncolbert--score
last_updated: 2026-05-24
---

# lightonai/Reason-ModernColBERT (Score)

Reason-ModernColBERT is a late interaction model trained on the reasonir-hq dataset. It achieves extremely competitive performance on the BRIGHT benchmark aimed at evaluating reasoning-intensive retrieval performance, outperforming all existing models up to 7B (more than 45 times its size) and ev...

Source: [lightonai/Reason-ModernColBERT on HuggingFace](https://huggingface.co/lightonai/Reason-ModernColBERT)
Base model: [lightonai/GTE-ModernColBERT-v1](https://huggingface.co/lightonai/GTE-ModernColBERT-v1)

## Overview

| Field | Value |
|-------|-------|
| Architecture | ModernBERT |
| Parameters | 149M |
| Tasks | Encode, Score |
| Outputs | Multi-Vec |
| Dimensions | Multi-Vec: 128 |
| Max sequence length | 8,192 tokens |
| License | cc-by-nc-4.0 |
| Inputs | text |
| Languages | en |

## Benchmarks

### AskUbuntuDupQuestions

Domain: technology · Task: reranking · Language: en

Duplicate question detection from AskUbuntu

Corpus: 6,743 · Queries: 360

**Quality:** ndcg at 10: 0.6520 · map at 10: 0.4972 · mrr at 10: 0.7335

[Reference](https://github.com/taolei87/askubuntu)

### CMedQAv1-reranking

Domain: general · Task: reranking · Language: en

**Quality:** ndcg at 10: 0.4245 · map at 10: 0.3554 · mrr at 10: 0.4450

### CMedQAv2-reranking

Domain: general · Task: reranking · Language: en

**Quality:** ndcg at 10: 0.4482 · map at 10: 0.3825 · mrr at 10: 0.4718

### MMarcoReranking

Domain: general · Task: reranking · Language: zh

Multilingual MARCO passage reranking (Chinese)

**Quality:** ndcg at 10: 0.1861 · map at 10: 0.1491 · mrr at 10: 0.1551

[Reference](https://arxiv.org/abs/2304.03679)