Contextual AI Rerank v2 Instruct vs Voyage AI Rerank 2.5
Detailed comparison between Contextual AI Rerank v2 Instruct and Voyage AI Rerank 2.5. See which reranker best meets your accuracy and performance needs. If you want to compare these models on your data, try Agentset.
Model Comparison
Voyage AI Rerank 2.5 takes the lead.
Both Contextual AI Rerank v2 Instruct and Voyage AI Rerank 2.5 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:
- Voyage AI Rerank 2.5 has 75 higher ELO rating
- Voyage AI Rerank 2.5 is 2720ms faster on average
- Voyage AI Rerank 2.5 has a 15.7% higher win rate
Overview
Key metrics
ELO Rating
Overall ranking quality
Contextual AI Rerank v2 Instruct
Voyage AI Rerank 2.5
Win Rate
Head-to-head performance
Contextual AI Rerank v2 Instruct
Voyage AI Rerank 2.5
Accuracy (nDCG@10)
Ranking quality metric
Contextual AI Rerank v2 Instruct
Voyage AI Rerank 2.5
Average Latency
Response time
Contextual AI Rerank v2 Instruct
Voyage AI Rerank 2.5
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 | Contextual AI Rerank v2 Instruct | Voyage AI Rerank 2.5 | Description |
|---|---|---|---|
| Overall Performance | |||
| ELO Rating | 1469 | 1544 | Overall ranking quality based on pairwise comparisons |
| Win Rate | 42.3% | 58.0% | Percentage of comparisons won against other models |
| Pricing & Availability | |||
| Price per 1M tokens | $0.050 | $0.050 | Cost per million tokens processed |
| Release Date | 2025-09-12 | 2025-08-11 | Model release date |
| Accuracy Metrics | |||
| Avg nDCG@10 | 0.114 | 0.110 | Normalized discounted cumulative gain at position 10 |
| Performance Metrics | |||
| Avg Latency | 3333ms | 613ms | 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 | Contextual AI Rerank v2 Instruct | Voyage AI Rerank 2.5 | Description |
|---|---|---|---|
| Latency Metrics | |||
| Mean | 3283ms | 571ms | Average response time |
| P50 | 3260ms | 611ms | 50th percentile (median) |
| P90 | 3885ms | 647ms | 90th percentile |
arguana
| Metric | Contextual AI Rerank v2 Instruct | Voyage AI Rerank 2.5 | Description |
|---|---|---|---|
| Accuracy Metrics | |||
| nDCG@5 | 0.525 | 0.536 | Ranking quality at top 5 results |
| nDCG@10 | 0.560 | 0.543 | Ranking quality at top 10 results |
| Recall@5 | 0.860 | 0.960 | % of relevant docs in top 5 |
| Recall@10 | 0.960 | 0.980 | % of relevant docs in top 10 |
| Latency Metrics | |||
| Mean | 3627ms | 675ms | Average response time |
| P50 | 3601ms | 612ms | 50th percentile (median) |
| P90 | 4037ms | 820ms | 90th percentile |
FiQa
| Metric | Contextual AI Rerank v2 Instruct | Voyage AI Rerank 2.5 | Description |
|---|---|---|---|
| Accuracy Metrics | |||
| nDCG@5 | 0.119 | 0.108 | Ranking quality at top 5 results |
| nDCG@10 | 0.125 | 0.119 | Ranking quality at top 10 results |
| Recall@5 | 0.123 | 0.098 | % of relevant docs in top 5 |
| Recall@10 | 0.135 | 0.128 | % of relevant docs in top 10 |
| Latency Metrics | |||
| Mean | 3283ms | 627ms | Average response time |
| P50 | 3209ms | 611ms | 50th percentile (median) |
| P90 | 3891ms | 814ms | 90th percentile |
business reports
| Metric | Contextual AI Rerank v2 Instruct | Voyage AI Rerank 2.5 | Description |
|---|---|---|---|
| Latency Metrics | |||
| Mean | 3231ms | 612ms | Average response time |
| P50 | 3129ms | 521ms | 50th percentile (median) |
| P90 | 3651ms | 734ms | 90th percentile |
PG
| Metric | Contextual AI Rerank v2 Instruct | Voyage AI Rerank 2.5 | Description |
|---|---|---|---|
| Latency Metrics | |||
| Mean | 3566ms | 612ms | Average response time |
| P50 | 3475ms | 612ms | 50th percentile (median) |
| P90 | 4148ms | 791ms | 90th percentile |
DBPedia
| Metric | Contextual AI Rerank v2 Instruct | Voyage AI Rerank 2.5 | Description |
|---|---|---|---|
| Latency Metrics | |||
| Mean | 3010ms | 583ms | Average response time |
| P50 | 3042ms | 613ms | 50th percentile (median) |
| P90 | 3283ms | 632ms | 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.