Voyage AI Rerank 2.5 Lite vs Cohere Rerank 3.5

Detailed comparison between Voyage AI Rerank 2.5 Lite and Cohere Rerank 3.5. 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 Cohere Rerank 3.5 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 76 higher ELO rating
  • Voyage AI Rerank 2.5 Lite delivers better accuracy (nDCG@10: 0.226 vs 0.200)
  • Voyage AI Rerank 2.5 Lite has a 12.1% higher win rate

Overview

Key metrics

ELO Rating

Overall ranking quality

Voyage AI Rerank 2.5 Lite

1528

Cohere Rerank 3.5

1452

Win Rate

Head-to-head performance

Voyage AI Rerank 2.5 Lite

53.1%

Cohere Rerank 3.5

41.0%

Accuracy (nDCG@10)

Ranking quality metric

Voyage AI Rerank 2.5 Lite

0.226

Cohere Rerank 3.5

0.200

Average Latency

Response time

Voyage AI Rerank 2.5 Lite

616ms

Cohere Rerank 3.5

392ms

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 LiteCohere Rerank 3.5Description
Overall Performance
ELO Rating
1528
1452
Overall ranking quality based on pairwise comparisons
Win Rate
53.1%
41.0%
Percentage of comparisons won against other models
Pricing & Availability
Price per 1M tokens
$0.020
$0.050
Cost per million tokens processed
Release Date
2025-08-11
2024-12-02
Model release date
Accuracy Metrics
Avg nDCG@10
0.226
0.200
Normalized discounted cumulative gain at position 10
Performance Metrics
Avg Latency
616ms
392ms
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

MetricVoyage AI Rerank 2.5 LiteCohere Rerank 3.5Description
Accuracy Metrics
nDCG@5
0.577
0.522
Ranking quality at top 5 results
nDCG@10
0.585
0.553
Ranking quality at top 10 results
Recall@5
0.780
0.700
% of relevant docs in top 5
Recall@10
0.800
0.800
% of relevant docs in top 10
Latency Metrics
Mean
563ms
339ms
Average response time
P50
610ms
285ms
50th percentile (median)
P90
619ms
304ms
90th percentile

arguana

MetricVoyage AI Rerank 2.5 LiteCohere Rerank 3.5Description
Accuracy Metrics
nDCG@5
0.436
0.267
Ranking quality at top 5 results
nDCG@10
0.496
0.355
Ranking quality at top 10 results
Recall@5
0.800
0.520
% of relevant docs in top 5
Recall@10
0.980
0.800
% of relevant docs in top 10
Latency Metrics
Mean
636ms
570ms
Average response time
P50
613ms
373ms
50th percentile (median)
P90
819ms
617ms
90th percentile

FiQa

MetricVoyage AI Rerank 2.5 LiteCohere Rerank 3.5Description
Accuracy Metrics
nDCG@5
0.111
0.124
Ranking quality at top 5 results
nDCG@10
0.122
0.128
Ranking quality at top 10 results
Recall@5
0.103
0.123
% of relevant docs in top 5
Recall@10
0.135
0.130
% of relevant docs in top 10
Latency Metrics
Mean
639ms
364ms
Average response time
P50
613ms
315ms
50th percentile (median)
P90
819ms
401ms
90th percentile

business reports

MetricVoyage AI Rerank 2.5 LiteCohere Rerank 3.5Description
Latency Metrics
Mean
599ms
334ms
Average response time
P50
611ms
293ms
50th percentile (median)
P90
727ms
503ms
90th percentile

PG

MetricVoyage AI Rerank 2.5 LiteCohere Rerank 3.5Description
Latency Metrics
Mean
670ms
458ms
Average response time
P50
615ms
360ms
50th percentile (median)
P90
818ms
615ms
90th percentile

DBPedia

MetricVoyage AI Rerank 2.5 LiteCohere Rerank 3.5Description
Accuracy Metrics
nDCG@5
0.146
0.156
Ranking quality at top 5 results
nDCG@10
0.156
0.166
Ranking quality at top 10 results
Recall@5
0.004
0.004
% of relevant docs in top 5
Recall@10
0.005
0.005
% of relevant docs in top 10
Latency Metrics
Mean
587ms
286ms
Average response time
P50
612ms
279ms
50th percentile (median)
P90
656ms
290ms
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.