Voyage AI Rerank 2.5 Lite vs BAAI/BGE Reranker v2 M3

Detailed comparison between Voyage AI Rerank 2.5 Lite and BAAI/BGE Reranker v2 M3. See which reranker best meets your accuracy and performance needs.

Model Comparison

Voyage AI Rerank 2.5 Lite takes the lead.

Both Voyage AI Rerank 2.5 Lite and BAAI/BGE Reranker v2 M3 are powerful reranking models designed to improve retrieval quality in RAG applications. However, their performance characteristics differ in important ways.

Why Voyage AI Rerank 2.5 Lite:

  • Voyage AI Rerank 2.5 Lite has 42 higher ELO rating
  • Voyage AI Rerank 2.5 Lite is 1284ms faster on average
  • Voyage AI Rerank 2.5 Lite has a 17.4% higher win rate

Overview

Key metrics

ELO Rating

Overall ranking quality

Voyage AI Rerank 2.5 Lite

1510

BAAI/BGE Reranker v2 M3

1468

Win Rate

Head-to-head performance

Voyage AI Rerank 2.5 Lite

50.4%

BAAI/BGE Reranker v2 M3

33.0%

Accuracy (nDCG@10)

Ranking quality metric

Voyage AI Rerank 2.5 Lite

0.679

BAAI/BGE Reranker v2 M3

0.686

Average Latency

Response time

Voyage AI Rerank 2.5 Lite

607ms

BAAI/BGE Reranker v2 M3

1891ms

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

MetricVoyage AI Rerank 2.5 LiteBAAI/BGE Reranker v2 M3Description
Overall Performance
ELO Rating
1510
1468
Overall ranking quality based on pairwise comparisons
Win Rate
50.4%
33.0%
Percentage of comparisons won against other models
Pricing & Availability
Price per 1M tokens
$0.020
$0.020
Cost per million tokens processed
Release Date
2025-08-11
2023-09-15
Model release date
Accuracy Metrics
Avg nDCG@10
0.679
0.686
Normalized discounted cumulative gain at position 10
Performance Metrics
Avg Latency
607ms
1891ms
Average response time across all datasets

Dataset Performance

By field

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

FiQa

MetricVoyage AI Rerank 2.5 LiteBAAI/BGE Reranker v2 M3Description
Accuracy Metrics
nDCG@5
0.111
0.112
Ranking quality at top 5 results
nDCG@10
0.122
0.120
Ranking quality at top 10 results
Recall@5
0.103
0.105
% of relevant docs in top 5
Recall@10
0.135
0.130
% of relevant docs in top 10
Latency Metrics
Mean
686ms
1309ms
Average response time
P50
611ms
1316ms
50th percentile (median)
P90
829ms
1744ms
90th percentile

Scifact

MetricVoyage AI Rerank 2.5 LiteBAAI/BGE Reranker v2 M3Description
Accuracy Metrics
nDCG@5
0.844
0.843
Ranking quality at top 5 results
nDCG@10
0.849
0.860
Ranking quality at top 10 results
Recall@5
0.892
0.863
% of relevant docs in top 5
Recall@10
0.900
0.906
% of relevant docs in top 10
Latency Metrics
Mean
642ms
2928ms
Average response time
P50
618ms
1581ms
50th percentile (median)
P90
816ms
1862ms
90th percentile

PG

MetricVoyage AI Rerank 2.5 LiteBAAI/BGE Reranker v2 M3Description
Accuracy Metrics
Latency Metrics
Mean
637ms
2457ms
Average response time
P50
614ms
1019ms
50th percentile (median)
P90
817ms
1469ms
90th percentile

business reports

MetricVoyage AI Rerank 2.5 LiteBAAI/BGE Reranker v2 M3Description
Accuracy Metrics
Latency Metrics
Mean
580ms
1143ms
Average response time
P50
607ms
1106ms
50th percentile (median)
P90
816ms
1641ms
90th percentile

MSMARCO

MetricVoyage AI Rerank 2.5 LiteBAAI/BGE Reranker v2 M3Description
Accuracy Metrics
nDCG@5
0.981
0.985
Ranking quality at top 5 results
nDCG@10
0.983
0.985
Ranking quality at top 10 results
Recall@5
0.993
1.000
% of relevant docs in top 5
Recall@10
1.000
1.000
% of relevant docs in top 10
Latency Metrics
Mean
542ms
2176ms
Average response time
P50
611ms
812ms
50th percentile (median)
P90
635ms
980ms
90th percentile

DBPedia

MetricVoyage AI Rerank 2.5 LiteBAAI/BGE Reranker v2 M3Description
Accuracy Metrics
nDCG@5
0.692
0.715
Ranking quality at top 5 results
nDCG@10
0.763
0.778
Ranking quality at top 10 results
Recall@5
0.064
0.063
% of relevant docs in top 5
Recall@10
0.111
0.106
% of relevant docs in top 10
Latency Metrics
Mean
555ms
1332ms
Average response time
P50
605ms
831ms
50th percentile (median)
P90
664ms
1455ms
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.