Voyage AI Rerank 2.5 Lite vs Cohere Rerank 4 Pro
Detailed comparison between Voyage AI Rerank 2.5 Lite and Cohere Rerank 4 Pro. See which reranker best meets your accuracy and performance needs. If you want to compare these models on your data, try Agentset.
Model Comparison
Cohere Rerank 4 Pro takes the lead.
Both Voyage AI Rerank 2.5 Lite 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 109 higher ELO rating
Overview
Key metrics
ELO Rating
Overall ranking quality
Voyage AI Rerank 2.5 Lite
Cohere Rerank 4 Pro
Win Rate
Head-to-head performance
Voyage AI Rerank 2.5 Lite
Cohere Rerank 4 Pro
Accuracy (nDCG@10)
Ranking quality metric
Voyage AI Rerank 2.5 Lite
Cohere Rerank 4 Pro
Average Latency
Response time
Voyage AI Rerank 2.5 Lite
Cohere Rerank 4 Pro
Rerankers Are Just One Piece of RAG
Agentset gives you a managed RAG pipeline with the top-ranked models and best practices baked in. No infrastructure to maintain, no reranking to configure.
Trusted by teams building production RAG applications
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
| Metric | Voyage AI Rerank 2.5 Lite | Cohere Rerank 4 Pro | Description |
|---|---|---|---|
| Overall Performance | |||
| ELO Rating | 1520 | 1629 | Overall ranking quality based on pairwise comparisons |
| Win Rate | 53.4% | 57.7% | 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 | 2025-12-11 | Model release date |
| Accuracy Metrics | |||
| Avg nDCG@10 | 0.103 | 0.095 | Normalized discounted cumulative gain at position 10 |
| Performance Metrics | |||
| Avg Latency | 616ms | 614ms | Average response time across all datasets |
Build RAG in Minutes, Not Months
Agentset gives you a complete RAG API with top-ranked rerankers and embedding models built in. Upload your data, call the API, and get accurate results from day one.
import { Agentset } from "agentset";
const agentset = new Agentset();
const ns = agentset.namespace("ns_1234");
const results = await ns.search(
"What is multi-head attention?"
);
for (const result of results) {
console.log(result.text);
}Dataset Performance
By field
Comprehensive comparison of accuracy metrics (nDCG, Recall) and latency percentiles for each benchmark dataset.
MSMARCO
| Metric | Voyage AI Rerank 2.5 Lite | Cohere Rerank 4 Pro | Description |
|---|---|---|---|
| Latency Metrics | |||
| Mean | 563ms | 458ms | Average response time |
| P50 | 610ms | 408ms | 50th percentile (median) |
| P90 | 619ms | 615ms | 90th percentile |
arguana
| Metric | Voyage AI Rerank 2.5 Lite | Cohere Rerank 4 Pro | Description |
|---|---|---|---|
| Accuracy Metrics | |||
| nDCG@5 | 0.436 | 0.353 | Ranking quality at top 5 results |
| nDCG@10 | 0.496 | 0.439 | Ranking quality at top 10 results |
| Recall@5 | 0.800 | 0.660 | % of relevant docs in top 5 |
| Recall@10 | 0.980 | 0.920 | % of relevant docs in top 10 |
| Latency Metrics | |||
| Mean | 636ms | 785ms | Average response time |
| P50 | 613ms | 768ms | 50th percentile (median) |
| P90 | 819ms | 933ms | 90th percentile |
FiQa
| Metric | Voyage AI Rerank 2.5 Lite | Cohere Rerank 4 Pro | Description |
|---|---|---|---|
| Accuracy Metrics | |||
| nDCG@5 | 0.111 | 0.126 | Ranking quality at top 5 results |
| nDCG@10 | 0.122 | 0.129 | Ranking quality at top 10 results |
| Recall@5 | 0.103 | 0.130 | % of relevant docs in top 5 |
| Recall@10 | 0.135 | 0.135 | % of relevant docs in top 10 |
| Latency Metrics | |||
| Mean | 639ms | 610ms | Average response time |
| P50 | 613ms | 585ms | 50th percentile (median) |
| P90 | 819ms | 817ms | 90th percentile |
business reports
| Metric | Voyage AI Rerank 2.5 Lite | Cohere Rerank 4 Pro | Description |
|---|---|---|---|
| Latency Metrics | |||
| Mean | 599ms | 529ms | Average response time |
| P50 | 611ms | 498ms | 50th percentile (median) |
| P90 | 727ms | 675ms | 90th percentile |
PG
| Metric | Voyage AI Rerank 2.5 Lite | Cohere Rerank 4 Pro | Description |
|---|---|---|---|
| Latency Metrics | |||
| Mean | 670ms | 760ms | Average response time |
| P50 | 615ms | 720ms | 50th percentile (median) |
| P90 | 818ms | 896ms | 90th percentile |
DBPedia
| Metric | Voyage AI Rerank 2.5 Lite | Cohere Rerank 4 Pro | Description |
|---|---|---|---|
| Latency Metrics | |||
| Mean | 587ms | 541ms | Average response time |
| P50 | 612ms | 489ms | 50th percentile (median) |
| P90 | 656ms | 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.