Cohere Rerank 4 Pro vs Jina Reranker v2 Base Multilingual

Detailed comparison between Cohere Rerank 4 Pro and Jina Reranker v2 Base Multilingual. 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 Cohere Rerank 4 Pro 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 Cohere Rerank 4 Pro:

  • Cohere Rerank 4 Pro has 302 higher ELO rating
  • Cohere Rerank 4 Pro delivers better accuracy (nDCG@10: 0.095 vs 0.080)
  • Cohere Rerank 4 Pro is 133ms faster on average
  • Cohere Rerank 4 Pro has a 29.5% higher win rate

Overview

Key metrics

ELO Rating

Overall ranking quality

Cohere Rerank 4 Pro

1629

Jina Reranker v2 Base Multilingual

1327

Win Rate

Head-to-head performance

Cohere Rerank 4 Pro

57.7%

Jina Reranker v2 Base Multilingual

28.2%

Accuracy (nDCG@10)

Ranking quality metric

Cohere Rerank 4 Pro

0.095

Jina Reranker v2 Base Multilingual

0.080

Average Latency

Response time

Cohere Rerank 4 Pro

614ms

Jina Reranker v2 Base Multilingual

746ms

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

5M+
Documents
1,500+
Teams
99.9%
Uptime

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

MetricCohere Rerank 4 ProJina Reranker v2 Base MultilingualDescription
Overall Performance
ELO Rating
1629
1327
Overall ranking quality based on pairwise comparisons
Win Rate
57.7%
28.2%
Percentage of comparisons won against other models
Pricing & Availability
Price per 1M tokens
$0.050
$0.045
Cost per million tokens processed
Release Date
2025-12-11
2024-06-25
Model release date
Accuracy Metrics
Avg nDCG@10
0.095
0.080
Normalized discounted cumulative gain at position 10
Performance Metrics
Avg Latency
614ms
746ms
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

MetricCohere Rerank 4 ProJina Reranker v2 Base MultilingualDescription
Latency Metrics
Mean
458ms
694ms
Average response time
P50
408ms
616ms
50th percentile (median)
P90
615ms
911ms
90th percentile

arguana

MetricCohere Rerank 4 ProJina Reranker v2 Base MultilingualDescription
Accuracy Metrics
nDCG@5
0.353
0.314
Ranking quality at top 5 results
nDCG@10
0.439
0.374
Ranking quality at top 10 results
Recall@5
0.660
0.580
% of relevant docs in top 5
Recall@10
0.920
0.760
% of relevant docs in top 10
Latency Metrics
Mean
785ms
689ms
Average response time
P50
768ms
617ms
50th percentile (median)
P90
933ms
834ms
90th percentile

FiQa

MetricCohere Rerank 4 ProJina Reranker v2 Base MultilingualDescription
Accuracy Metrics
nDCG@5
0.126
0.105
Ranking quality at top 5 results
nDCG@10
0.129
0.108
Ranking quality at top 10 results
Recall@5
0.130
0.088
% of relevant docs in top 5
Recall@10
0.135
0.093
% of relevant docs in top 10
Latency Metrics
Mean
610ms
676ms
Average response time
P50
585ms
626ms
50th percentile (median)
P90
817ms
837ms
90th percentile

business reports

MetricCohere Rerank 4 ProJina Reranker v2 Base MultilingualDescription
Latency Metrics
Mean
529ms
690ms
Average response time
P50
498ms
620ms
50th percentile (median)
P90
675ms
824ms
90th percentile

PG

MetricCohere Rerank 4 ProJina Reranker v2 Base MultilingualDescription
Latency Metrics
Mean
760ms
1059ms
Average response time
P50
720ms
823ms
50th percentile (median)
P90
896ms
1744ms
90th percentile

DBPedia

MetricCohere Rerank 4 ProJina Reranker v2 Base MultilingualDescription
Latency Metrics
Mean
541ms
671ms
Average response time
P50
489ms
614ms
50th percentile (median)
P90
729ms
825ms
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.