---
title: cross-encoder/ms-marco-MiniLM-L-12-v2
description: This model was trained on the MS Marco Passage Ranking task.. BERT, 33M parameters.
canonical_url: https://superlinked.com/models/cross-encoder-ms-marco-minilm-l-12-v2
last_updated: 2026-05-25
---

# cross-encoder/ms-marco-MiniLM-L-12-v2

This model was trained on the MS Marco Passage Ranking task.

Source: [cross-encoder/ms-marco-MiniLM-L-12-v2 on HuggingFace](https://huggingface.co/cross-encoder/ms-marco-MiniLM-L-12-v2)
Base model: [microsoft/MiniLM-L12-H384-uncased](https://huggingface.co/microsoft/MiniLM-L12-H384-uncased)

## Overview

| Field | Value |
|-------|-------|
| Architecture | BERT |
| Parameters | 33M |
| Tasks | Score |
| Outputs | Score |
| Max sequence length | 512 tokens |
| License | apache-2.0 |
| 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: 0.6145 · map at 10: 0.4558 · mrr at 10: 0.6921

**Performance (L4 b1 c16):** Query 8.2K tok/s · Query p50 31.7ms

[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: 0.1016 · mrr at 10: 0.1528

[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: 0.1218 · mrr at 10: 0.1812

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

### MMarcoReranking

Domain: general · Task: reranking · Language: zh

Multilingual MARCO passage reranking (Chinese)

**Quality:** map at 10: 0.0426 · mrr at 10: 0.0446

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

### T2Reranking

Domain: general · Task: reranking · Language: zh

Chinese passage ranking benchmark

**Quality:** map at 10: 0.5184 · mrr at 10: 0.7511

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