Back to all rerankers

BAAI/BGE Reranker v2 M3

Lightweight 0.6B parameter cross-encoder built on bge-m3 foundation with LoRA fine-tuning and flash attention optimization. Strong multilingual support with fast inference, trained on diverse datasets including FEVER and MIRACL for production deployment efficiency. If you want to compare the best rerankers for your data, try Agentset.

Leaderboard Rank
#11
of 12
ELO Rating
1327
#11
Win Rate
28.6%
#11
Accuracy (nDCG@10)
0.084
#7
Latency
2383ms
#10

Model Information

Provider
BAAI
License
Open Source
Price per 1M tokens
$0.020
Release Date
2023-09-15
Model Name
bge-reranker-v2-m3
Total Evaluations
3300

Performance Record

Wins945 (28.6%)
Losses2289 (69.4%)
Ties66 (2.0%)
Wins
Losses
Ties

Rerankers Are Just One Piece of RAG

Agentset gives you a managed RAG pipeline with the top-ranked models and best practices baked in. No infrastructure to maintain, no reranking to configure.

Trusted by teams building production RAG applications

5M+
Documents
1,500+
Teams
99.9%
Uptime

Performance Overview

ELO ratings by dataset

BAAI/BGE Reranker v2 M3's ELO performance varies across different benchmark datasets, showing its strengths in specific domains.

BAAI/BGE Reranker v2 M3 - ELO by Dataset

Detailed Metrics

Dataset breakdown

Performance metrics across different benchmark datasets, including accuracy and latency percentiles.

MSMARCO

ELO 143738.9% WR214W-307L-29T

Accuracy Metrics

nDCG@5
0.000
nDCG@10
0.000
Recall@5
0.000
Recall@10
0.000

Latency Distribution

Mean
2207ms
P50 (Median)
825ms
P90
1247ms

business reports

ELO 142039.3% WR216W-327L-7T

Accuracy Metrics

nDCG@5
0.000
nDCG@10
0.000
Recall@5
0.000
Recall@10
0.000

Latency Distribution

Mean
2451ms
P50 (Median)
895ms
P90
1679ms

PG

ELO 136429.3% WR161W-388L-1T

Accuracy Metrics

nDCG@5
0.000
nDCG@10
0.000
Recall@5
0.000
Recall@10
0.000

Latency Distribution

Mean
2034ms
P50 (Median)
1225ms
P90
2091ms

DBPedia

ELO 134620.0% WR110W-422L-18T

Accuracy Metrics

nDCG@5
0.000
nDCG@10
0.000
Recall@5
0.000
Recall@10
0.000

Latency Distribution

Mean
2087ms
P50 (Median)
806ms
P90
1068ms

FiQa

ELO 128934.0% WR187W-353L-10T

Accuracy Metrics

nDCG@5
0.112
nDCG@10
0.120
Recall@5
0.105
Recall@10
0.130

Latency Distribution

Mean
2529ms
P50 (Median)
1019ms
P90
1649ms

arguana

ELO 110610.4% WR57W-492L-1T

Accuracy Metrics

nDCG@5
0.312
nDCG@10
0.386
Recall@5
0.560
Recall@10
0.780

Latency Distribution

Mean
2989ms
P50 (Median)
1658ms
P90
2279ms

Build RAG in Minutes, Not Months

Agentset gives you a complete RAG API with top-ranked rerankers and embedding models built in. Upload your data, call the API, and get accurate results from day one.

import { Agentset } from "agentset";

const agentset = new Agentset();
const ns = agentset.namespace("ns_1234");

const results = await ns.search(
  "What is multi-head attention?"
);

for (const result of results) {
  console.log(result.text);
}

Compare Models

See how it stacks up

Compare BAAI/BGE Reranker v2 M3 with other top rerankers to understand the differences in performance, accuracy, and latency.