Voyage AI Rerank 2.5 Lite vs Jina Reranker v2 Base Multilingual

Detailed comparison between Voyage AI Rerank 2.5 Lite and Jina Reranker v2 Base Multilingual. 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 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 Voyage AI Rerank 2.5 Lite:

  • Voyage AI Rerank 2.5 Lite has 175 higher ELO rating
  • Voyage AI Rerank 2.5 Lite is 804ms faster on average
  • Voyage AI Rerank 2.5 Lite has a 12.6% higher win rate

Overview

Key metrics

ELO Rating

Overall ranking quality

Voyage AI Rerank 2.5 Lite

1510

Jina Reranker v2 Base Multilingual

1335

Win Rate

Head-to-head performance

Voyage AI Rerank 2.5 Lite

50.4%

Jina Reranker v2 Base Multilingual

37.8%

Accuracy (nDCG@10)

Ranking quality metric

Voyage AI Rerank 2.5 Lite

0.679

Jina Reranker v2 Base Multilingual

0.671

Average Latency

Response time

Voyage AI Rerank 2.5 Lite

607ms

Jina Reranker v2 Base Multilingual

1411ms

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 LiteJina Reranker v2 Base MultilingualDescription
Overall Performance
ELO Rating
1510
1335
Overall ranking quality based on pairwise comparisons
Win Rate
50.4%
37.8%
Percentage of comparisons won against other models
Pricing & Availability
Price per 1M tokens
$0.020
$0.045
Cost per million tokens processed
Release Date
2025-08-11
2024-06-25
Model release date
Accuracy Metrics
Avg nDCG@10
0.679
0.671
Normalized discounted cumulative gain at position 10
Performance Metrics
Avg Latency
607ms
1411ms
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 LiteJina Reranker v2 Base MultilingualDescription
Accuracy Metrics
nDCG@5
0.111
0.112
Ranking quality at top 5 results
nDCG@10
0.122
0.121
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
2294ms
Average response time
P50
611ms
1949ms
50th percentile (median)
P90
829ms
4906ms
90th percentile

PG

MetricVoyage AI Rerank 2.5 LiteJina Reranker v2 Base MultilingualDescription
Accuracy Metrics
Latency Metrics
Mean
637ms
994ms
Average response time
P50
614ms
839ms
50th percentile (median)
P90
817ms
1436ms
90th percentile

business reports

MetricVoyage AI Rerank 2.5 LiteJina Reranker v2 Base MultilingualDescription
Accuracy Metrics
Latency Metrics
Mean
580ms
2191ms
Average response time
P50
607ms
1237ms
50th percentile (median)
P90
816ms
5520ms
90th percentile

MSMARCO

MetricVoyage AI Rerank 2.5 LiteJina Reranker v2 Base MultilingualDescription
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
1100ms
Average response time
P50
611ms
1023ms
50th percentile (median)
P90
635ms
1642ms
90th percentile

DBPedia

MetricVoyage AI Rerank 2.5 LiteJina Reranker v2 Base MultilingualDescription
Accuracy Metrics
nDCG@5
0.692
0.677
Ranking quality at top 5 results
nDCG@10
0.763
0.744
Ranking quality at top 10 results
Recall@5
0.064
0.064
% of relevant docs in top 5
Recall@10
0.111
0.106
% of relevant docs in top 10
Latency Metrics
Mean
555ms
763ms
Average response time
P50
605ms
796ms
50th percentile (median)
P90
664ms
1021ms
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.