BAAI/BGE Reranker v2 M3 vs Jina Reranker v2 Base Multilingual

Detailed comparison between BAAI/BGE Reranker v2 M3 and Jina Reranker v2 Base Multilingual. See which reranker best meets your accuracy and performance needs.

Model Comparison

Jina Reranker v2 Base Multilingual takes the lead.

Both BAAI/BGE Reranker v2 M3 and Jina Reranker v2 Base Multilingual are powerful reranking models designed to improve retrieval quality in RAG applications. However, their performance characteristics differ in important ways.

Why Jina Reranker v2 Base Multilingual:

  • Jina Reranker v2 Base Multilingual is 1636ms faster on average

Overview

Key metrics

ELO Rating

Overall ranking quality

BAAI/BGE Reranker v2 M3

1314

Jina Reranker v2 Base Multilingual

1306

Win Rate

Head-to-head performance

BAAI/BGE Reranker v2 M3

28.8%

Jina Reranker v2 Base Multilingual

28.5%

Accuracy (nDCG@10)

Ranking quality metric

BAAI/BGE Reranker v2 M3

0.201

Jina Reranker v2 Base Multilingual

0.193

Average Latency

Response time

BAAI/BGE Reranker v2 M3

2383ms

Jina Reranker v2 Base Multilingual

746ms

Visual Performance Analysis

Performance

ELO Rating Comparison

Win/Loss/Tie Breakdown

Accuracy Across Datasets (nDCG@10)

Latency Distribution (ms)

Breakdown

How the models stack up

MetricBAAI/BGE Reranker v2 M3Jina Reranker v2 Base MultilingualDescription
Overall Performance
ELO Rating
1314
1306
Overall ranking quality based on pairwise comparisons
Win Rate
28.8%
28.5%
Percentage of comparisons won against other models
Pricing & Availability
Price per 1M tokens
$0.020
$0.045
Cost per million tokens processed
Release Date
2023-09-15
2024-06-25
Model release date
Accuracy Metrics
Avg nDCG@10
0.201
0.193
Normalized discounted cumulative gain at position 10
Performance Metrics
Avg Latency
2383ms
746ms
Average response time across all datasets

Dataset Performance

By field

Comprehensive comparison of accuracy metrics (nDCG, Recall) and latency percentiles for each benchmark dataset.

MSMARCO

MetricBAAI/BGE Reranker v2 M3Jina Reranker v2 Base MultilingualDescription
Accuracy Metrics
nDCG@5
0.592
0.499
Ranking quality at top 5 results
nDCG@10
0.605
0.539
Ranking quality at top 10 results
Recall@5
0.740
0.680
% of relevant docs in top 5
Recall@10
0.780
0.800
% of relevant docs in top 10
Latency Metrics
Mean
2207ms
694ms
Average response time
P50
825ms
616ms
50th percentile (median)
P90
1247ms
911ms
90th percentile

arguana

MetricBAAI/BGE Reranker v2 M3Jina Reranker v2 Base MultilingualDescription
Accuracy Metrics
nDCG@5
0.312
0.314
Ranking quality at top 5 results
nDCG@10
0.386
0.374
Ranking quality at top 10 results
Recall@5
0.560
0.580
% of relevant docs in top 5
Recall@10
0.780
0.760
% of relevant docs in top 10
Latency Metrics
Mean
2989ms
689ms
Average response time
P50
1658ms
617ms
50th percentile (median)
P90
2279ms
834ms
90th percentile

FiQa

MetricBAAI/BGE Reranker v2 M3Jina Reranker v2 Base MultilingualDescription
Accuracy Metrics
nDCG@5
0.112
0.105
Ranking quality at top 5 results
nDCG@10
0.120
0.108
Ranking quality at top 10 results
Recall@5
0.105
0.088
% of relevant docs in top 5
Recall@10
0.130
0.093
% of relevant docs in top 10
Latency Metrics
Mean
2529ms
676ms
Average response time
P50
1019ms
626ms
50th percentile (median)
P90
1649ms
837ms
90th percentile

business reports

MetricBAAI/BGE Reranker v2 M3Jina Reranker v2 Base MultilingualDescription
Latency Metrics
Mean
2451ms
690ms
Average response time
P50
895ms
620ms
50th percentile (median)
P90
1679ms
824ms
90th percentile

PG

MetricBAAI/BGE Reranker v2 M3Jina Reranker v2 Base MultilingualDescription
Latency Metrics
Mean
2034ms
1059ms
Average response time
P50
1225ms
823ms
50th percentile (median)
P90
2091ms
1744ms
90th percentile

DBPedia

MetricBAAI/BGE Reranker v2 M3Jina Reranker v2 Base MultilingualDescription
Accuracy Metrics
nDCG@5
0.096
0.128
Ranking quality at top 5 results
nDCG@10
0.096
0.136
Ranking quality at top 10 results
Recall@5
0.003
0.004
% of relevant docs in top 5
Recall@10
0.003
0.005
% of relevant docs in top 10
Latency Metrics
Mean
2087ms
671ms
Average response time
P50
806ms
614ms
50th percentile (median)
P90
1068ms
825ms
90th percentile

Explore More

Compare more rerankers

See how all reranking models stack up. Compare Cohere, Jina AI, Voyage, ZeRank, and more. View comprehensive benchmarks, compare performance metrics, and find the perfect reranker for your RAG application.