---
title: BAAI/bge-m3 (Score)
description: "For more details please refer to our github repo: https://github.com/FlagOpen/FlagEmbedding. XLM-RoBERTa, 568M parameters."
canonical_url: https://superlinked.com/models/baai-bge-m3--score
last_updated: 2026-05-25
---

# BAAI/bge-m3 (Score)

For more details please refer to our github repo: https://github.com/FlagOpen/FlagEmbedding

Source: [BAAI/bge-m3 on HuggingFace](https://huggingface.co/BAAI/bge-m3)

## Overview

| Field | Value |
|-------|-------|
| Architecture | XLM-RoBERTa |
| Parameters | 568M |
| Tasks | Encode, Score |
| Outputs | Dense, Sparse, Multi-Vec |
| Dimensions | Dense: 1,024, Sparse: 250,002, Multi-Vec: 1,024 |
| Max sequence length | 8,192 tokens |
| License | mit |
| Inputs | text |

## Benchmarks

### CQADupstackPhysicsRetrieval

Domain: scientific · Task: retrieval · Language: en

Duplicate question retrieval from StackExchange Physics

Corpus: 38,314 · Queries: 1,039

**Performance (L4 b1 c16):** Corpus 27.0K tok/s · Corpus p50 75.3ms · Query 2.6K tok/s · Query p50 55.2ms

[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

**Performance (L4 b1 c16):** Corpus 13.5K tok/s · Corpus p50 58.4ms · Query 1.5K tok/s · Query p50 57.6ms

[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

**Performance (L4 b1 c16):** Corpus 26.8K tok/s · Corpus p50 89.3ms · Query 2.9K tok/s · Query p50 55.8ms

[Reference](https://sites.google.com/view/fiqa/)

### LegalBenchConsumerContractsQA

Domain: legal · Task: retrieval · Language: en

Question answering on consumer contracts

Corpus: 153 · Queries: 396

**Performance (L4 b1 c16):** Corpus 36.7K tok/s · Corpus p50 224.8ms · Query 3.7K tok/s · Query p50 59.5ms

[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

**Performance (L4 b1 c16):** Corpus 34.4K tok/s · Corpus p50 137.4ms · Query 1.2K tok/s · Query p50 56.8ms

[Reference](https://www.cl.uni-heidelberg.de/statnlpgroup/nfcorpus/)

### NanoFiQA2018Retrieval

Domain: finance · Task: retrieval · Language: en

Smaller subset of the FiQA financial QA dataset

**Performance (L4 b1 c16):** Corpus 30.9K tok/s · Corpus p50 86.4ms · Query 2.8K tok/s · Query p50 54.9ms

[Reference](https://sites.google.com/view/fiqa/)

### SCIDOCS

Domain: scientific · Task: retrieval · Language: en

Citation prediction, document classification, and recommendation for scientific papers

Corpus: 25,656 · Queries: 1,000

**Performance (L4 b1 c16):** Corpus 31.0K tok/s · Corpus p50 101.1ms · Query 2.7K tok/s · Query p50 55.7ms

[Reference](https://allenai.org/data/scidocs)

### SciFact

Domain: scientific · Task: retrieval · Language: en

Scientific claim verification using research literature

Corpus: 5,183 · Queries: 300

**Performance (L4 b1 c16):** Corpus 32.2K tok/s · Corpus p50 126.9ms · Query 3.9K tok/s · Query p50 57.5ms

[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

**Performance (L4 b1 c16):** Corpus 29.5K tok/s · Corpus p50 118.6ms · Query 31.5K tok/s · Query p50 147.9ms

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