---
title: jinaai/jina-reranker-v2-base-multilingual
description: Trained by Jina AI.. XLM-RoBERTa, 278M parameters.
canonical_url: https://superlinked.com/models/jinaai-jina-reranker-v2-base-multilingual
last_updated: 2026-05-24
---

# jinaai/jina-reranker-v2-base-multilingual

Trained by Jina AI.

Source: [jinaai/jina-reranker-v2-base-multilingual on HuggingFace](https://huggingface.co/jinaai/jina-reranker-v2-base-multilingual)

## Overview

| Field | Value |
|-------|-------|
| Architecture | XLM-RoBERTa |
| Parameters | 278M |
| Tasks | Score |
| Outputs | Score |
| Max sequence length | 1,024 tokens |
| License | cc-by-nc-4.0 |
| Inputs | text |
| Languages | multilingual |

## Benchmarks

### AskUbuntuDupQuestions

Domain: technology · Task: reranking · Language: en

Duplicate question detection from AskUbuntu

Corpus: 6,743 · Queries: 360

**Quality:** ndcg at 10: 0.6546 · map at 10: 0.5008 · mrr at 10: 0.7429

**Performance (L4 b1 c16):** Query 8.3K tok/s · Query p50 32.0ms

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

### CMedQAv1Reranking

Domain: medical · Task: reranking · Language: zh

Chinese medical question answering reranking (v1)

Corpus: 100,000 · Queries: 2,000

**Quality:** map at 10: 0.2034 · mrr at 10: 0.2747

[Reference](https://github.com/zhangsheng93/cMedQA)

### CMedQAv2Reranking

Domain: medical · Task: reranking · Language: zh

Chinese medical question answering reranking (v2)

Corpus: 108,000 · Queries: 4,000

**Quality:** map at 10: 0.2063 · mrr at 10: 0.2837

[Reference](https://github.com/zhangsheng93/cMedQA2)

### MMarcoReranking

Domain: general · Task: reranking · Language: zh

Multilingual MARCO passage reranking (Chinese)

**Quality:** map at 10: 0.3433 · mrr at 10: 0.3622

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