BAAI/BGE Reranker v2 M3 vs Cohere Rerank 4 Pro

Detailed comparison between BAAI/BGE Reranker v2 M3 and Cohere Rerank 4 Pro. See which reranker best meets your accuracy and performance needs.

Model Comparison

Cohere Rerank 4 Pro takes the lead.

Both BAAI/BGE Reranker v2 M3 and Cohere Rerank 4 Pro are powerful reranking models designed to improve retrieval quality in RAG applications. However, their performance characteristics differ in important ways.

Why Cohere Rerank 4 Pro:

  • Cohere Rerank 4 Pro has 313 higher ELO rating
  • Cohere Rerank 4 Pro delivers better accuracy (nDCG@10: 0.219 vs 0.201)
  • Cohere Rerank 4 Pro is 1769ms faster on average
  • Cohere Rerank 4 Pro has a 29.4% higher win rate

Overview

Key metrics

ELO Rating

Overall ranking quality

BAAI/BGE Reranker v2 M3

1314

Cohere Rerank 4 Pro

1627

Win Rate

Head-to-head performance

BAAI/BGE Reranker v2 M3

28.8%

Cohere Rerank 4 Pro

58.2%

Accuracy (nDCG@10)

Ranking quality metric

BAAI/BGE Reranker v2 M3

0.201

Cohere Rerank 4 Pro

0.219

Average Latency

Response time

BAAI/BGE Reranker v2 M3

2383ms

Cohere Rerank 4 Pro

614ms

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 M3Cohere Rerank 4 ProDescription
Overall Performance
ELO Rating
1314
1627
Overall ranking quality based on pairwise comparisons
Win Rate
28.8%
58.2%
Percentage of comparisons won against other models
Pricing & Availability
Price per 1M tokens
$0.020
$0.050
Cost per million tokens processed
Release Date
2023-09-15
2025-12-11
Model release date
Accuracy Metrics
Avg nDCG@10
0.201
0.219
Normalized discounted cumulative gain at position 10
Performance Metrics
Avg Latency
2383ms
614ms
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 M3Cohere Rerank 4 ProDescription
Accuracy Metrics
nDCG@5
0.592
0.562
Ranking quality at top 5 results
nDCG@10
0.605
0.583
Ranking quality at top 10 results
Recall@5
0.740
0.740
% of relevant docs in top 5
Recall@10
0.780
0.800
% of relevant docs in top 10
Latency Metrics
Mean
2207ms
458ms
Average response time
P50
825ms
408ms
50th percentile (median)
P90
1247ms
615ms
90th percentile

arguana

MetricBAAI/BGE Reranker v2 M3Cohere Rerank 4 ProDescription
Accuracy Metrics
nDCG@5
0.312
0.353
Ranking quality at top 5 results
nDCG@10
0.386
0.439
Ranking quality at top 10 results
Recall@5
0.560
0.660
% of relevant docs in top 5
Recall@10
0.780
0.920
% of relevant docs in top 10
Latency Metrics
Mean
2989ms
785ms
Average response time
P50
1658ms
768ms
50th percentile (median)
P90
2279ms
933ms
90th percentile

FiQa

MetricBAAI/BGE Reranker v2 M3Cohere Rerank 4 ProDescription
Accuracy Metrics
nDCG@5
0.112
0.126
Ranking quality at top 5 results
nDCG@10
0.120
0.129
Ranking quality at top 10 results
Recall@5
0.105
0.130
% of relevant docs in top 5
Recall@10
0.130
0.135
% of relevant docs in top 10
Latency Metrics
Mean
2529ms
610ms
Average response time
P50
1019ms
585ms
50th percentile (median)
P90
1649ms
817ms
90th percentile

business reports

MetricBAAI/BGE Reranker v2 M3Cohere Rerank 4 ProDescription
Latency Metrics
Mean
2451ms
529ms
Average response time
P50
895ms
498ms
50th percentile (median)
P90
1679ms
675ms
90th percentile

PG

MetricBAAI/BGE Reranker v2 M3Cohere Rerank 4 ProDescription
Latency Metrics
Mean
2034ms
760ms
Average response time
P50
1225ms
720ms
50th percentile (median)
P90
2091ms
896ms
90th percentile

DBPedia

MetricBAAI/BGE Reranker v2 M3Cohere Rerank 4 ProDescription
Accuracy Metrics
nDCG@5
0.096
0.151
Ranking quality at top 5 results
nDCG@10
0.096
0.166
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
541ms
Average response time
P50
806ms
489ms
50th percentile (median)
P90
1068ms
729ms
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.