---
title: Reranker Models
description: Model selection guide for cross-encoder and ColBERT rerankers.
canonical_url: https://superlinked.com/docs/score/models
last_updated: 2026-05-20
---

## Supported Models

Source: [packages/sie_server/models/](https://github.com/superlinked/sie/blob/main/packages/sie_server/models/)

| Model | Max Length | Notes |
|-------|------------|-------|
| `BAAI/bge-reranker-v2-m3` | 8192 | Multilingual |
| `jinaai/jina-reranker-v2-base-multilingual` | 8192 | Multilingual |
| `Alibaba-NLP/gte-reranker-modernbert-base` | 8192 | ModernBERT architecture |
| `cross-encoder/ms-marco-MiniLM-L-12-v2` | 512 | Smaller, faster |

See [Full model catalog](/models#task=score) for the complete list.

## Model Selection

### By Language Support

**English only:**
- `BAAI/bge-reranker-base`, `BAAI/bge-reranker-large`
- `cross-encoder/ms-marco-MiniLM-L-6-v2`, `cross-encoder/ms-marco-MiniLM-L-12-v2`

**Multilingual (100+ languages):**
- `BAAI/bge-reranker-v2-m3`
- `jinaai/jina-reranker-v2-base-multilingual`
- `jinaai/jina-colbert-v2`

### By Context Length

**Short context (512 tokens):**
- `BAAI/bge-reranker-base`, `BAAI/bge-reranker-large`
- `cross-encoder/ms-marco-MiniLM-L-*`
- `colbert-ir/colbertv2.0`, `mixedbread-ai/mxbai-colbert-large-v1`

**Long context (8192 tokens):**
- `BAAI/bge-reranker-v2-m3`
- `jinaai/jina-reranker-v2-base-multilingual`
- `Alibaba-NLP/gte-reranker-modernbert-base`
- `mixedbread-ai/mxbai-rerank-base-v2`, `mixedbread-ai/mxbai-rerank-large-v2`
- `jinaai/jina-colbert-v2`, `lightonai/GTE-ModernColBERT-v1`, `lightonai/Reason-ModernColBERT`

### By Size

**Compact (fast inference):**
- `cross-encoder/ms-marco-MiniLM-L-6-v2` - smallest cross-encoder
- `mixedbread-ai/mxbai-edge-colbert-v0-32m` - 32M parameters
- `answerdotai/answerai-colbert-small-v1` - compact ColBERT

**Large (higher capacity):**
- `BAAI/bge-reranker-large`
- `mixedbread-ai/mxbai-rerank-large-v2`
- `mixedbread-ai/mxbai-colbert-large-v1`
- `lightonai/Reason-ModernColBERT` - long context (8192), ModernBERT family
- `nvidia/llama-nemoretriever-colembed-3b-v1` - 3B parameters

## Benchmarking

Use the eval harness to benchmark rerankers on your data:

```bash
# Quality evaluation
mise run eval BAAI/bge-reranker-v2-m3 -t mteb/AskUbuntuDupQuestions --type quality

# Performance evaluation
mise run eval BAAI/bge-reranker-v2-m3 -t mteb/AskUbuntuDupQuestions --type perf

# Compare multiple models
mise run eval BAAI/bge-reranker-base -t mteb/AskUbuntuDupQuestions --type quality
mise run eval cross-encoder/ms-marco-MiniLM-L-12-v2 -t mteb/AskUbuntuDupQuestions --type quality
```

## What's Next

- [Multi-vector reranking](/docs/score/multivector/) - ColBERT MaxSim scoring
- [Full model catalog](/models#task=score) - all supported models