Agentset

1.9k

Jina Embeddings v5 Text Small vs Cohere Embed Multilingual v3

Detailed comparison between Jina Embeddings v5 Text Small and Cohere Embed Multilingual v3. See which embedding best meets your accuracy and performance needs. If you want to compare these models on your data, try Agentset.

Explore Jina Embeddings v5 Text SmallExplore Cohere Embed Multilingual v3

Model Comparison

Jina Embeddings v5 Text Small takes the lead.

Both Jina Embeddings v5 Text Small and Cohere Embed Multilingual v3 are powerful embedding models designed to improve retrieval quality in RAG applications. However, their performance characteristics differ in important ways.

Why Jina Embeddings v5 Text Small:

  • Jina Embeddings v5 Text Small has 54 higher ELO rating
  • Cohere Embed Multilingual v3 delivers better accuracy (nDCG@10: 0.701 vs 0.608)
  • Cohere Embed Multilingual v3 is 281ms faster on average
  • Jina Embeddings v5 Text Small has a 6.3% higher win rate

Overview

Key metrics

ELO Rating

Overall ranking quality

Jina Embeddings v5 Text Small

1566

Cohere Embed Multilingual v3

1512

Win Rate

Head-to-head performance

Jina Embeddings v5 Text Small

54.7%

Cohere Embed Multilingual v3

48.4%

Accuracy (nDCG@10)

Ranking quality metric

Jina Embeddings v5 Text Small

0.608

Cohere Embed Multilingual v3

0.701

Average Latency

Response time

Jina Embeddings v5 Text Small

289ms

Cohere Embed Multilingual v3

7ms

Embedding Models 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 embeddings to manage.

Get started freeSchedule demo

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

MetricJina Embeddings v5 Text SmallCohere Embed Multilingual v3Description
Overall Performance
ELO Rating
1566
1512
Overall ranking quality based on pairwise comparisons
Win Rate
54.7%
48.4%
Percentage of comparisons won against other models
Pricing & Availability
Price per 1M tokens
$0.050
$0.100
Cost per million tokens processed
Dimensions
1024
512
Vector embedding dimensions (lower is more efficient)
Release Date
2026-02-18
2024-02-07
Model release date
Accuracy Metrics
Avg nDCG@10
0.608
0.701
Normalized discounted cumulative gain at position 10
Performance Metrics
Avg Latency
289ms
7ms
Average response time across all datasets

Build RAG in Minutes, Not Months

Agentset gives you a complete RAG API with top-ranked embedding models and smart retrieval built in. Upload your data, call the API, and get accurate results from day one.

Get started freeRead the docs 
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.

business reports

MetricJina Embeddings v5 Text SmallCohere Embed Multilingual v3Description
Accuracy Metrics
nDCG@5
0.000
0.000
Ranking quality at top 5 results
nDCG@10
0.000
0.000
Ranking quality at top 10 results
Recall@5
0.000
0.000
% of relevant docs in top 5
Recall@10
0.000
0.000
% of relevant docs in top 10
Latency Metrics
Mean
283ms
8ms
Average response time
P50
247ms
8ms
50th percentile (median)
P90
322ms
8ms
90th percentile

DBPedia

MetricJina Embeddings v5 Text SmallCohere Embed Multilingual v3Description
Accuracy Metrics
nDCG@5
0.823
0.786
Ranking quality at top 5 results
nDCG@10
0.805
0.783
Ranking quality at top 10 results
Recall@5
0.062
0.061
% of relevant docs in top 5
Recall@10
0.123
0.122
% of relevant docs in top 10
Latency Metrics
Mean
270ms
7ms
Average response time
P50
239ms
7ms
50th percentile (median)
P90
264ms
7ms
90th percentile

FiQa

MetricJina Embeddings v5 Text SmallCohere Embed Multilingual v3Description
Accuracy Metrics
nDCG@5
0.838
0.804
Ranking quality at top 5 results
nDCG@10
0.831
0.812
Ranking quality at top 10 results
Recall@5
0.677
0.624
% of relevant docs in top 5
Recall@10
0.771
0.696
% of relevant docs in top 10
Latency Metrics
Mean
300ms
7ms
Average response time
P50
241ms
7ms
50th percentile (median)
P90
419ms
7ms
90th percentile

SciFact

MetricJina Embeddings v5 Text SmallCohere Embed Multilingual v3Description
Accuracy Metrics
nDCG@5
0.703
0.696
Ranking quality at top 5 results
nDCG@10
0.734
0.702
Ranking quality at top 10 results
Recall@5
0.789
0.804
% of relevant docs in top 5
Recall@10
0.898
0.830
% of relevant docs in top 10
Latency Metrics
Mean
267ms
7ms
Average response time
P50
240ms
7ms
50th percentile (median)
P90
265ms
7ms
90th percentile

MSMARCO

MetricJina Embeddings v5 Text SmallCohere Embed Multilingual v3Description
Accuracy Metrics
nDCG@5
0.960
0.952
Ranking quality at top 5 results
nDCG@10
0.954
0.941
Ranking quality at top 10 results
Recall@5
0.122
0.121
% of relevant docs in top 5
Recall@10
0.219
0.218
% of relevant docs in top 10
Latency Metrics
Mean
273ms
8ms
Average response time
P50
239ms
8ms
50th percentile (median)
P90
313ms
8ms
90th percentile

ARCD

MetricJina Embeddings v5 Text SmallCohere Embed Multilingual v3Description
Accuracy Metrics
nDCG@5
0.842
0.868
Ranking quality at top 5 results
nDCG@10
0.842
0.875
Ranking quality at top 10 results
Recall@5
0.940
0.940
% of relevant docs in top 5
Recall@10
0.940
0.960
% of relevant docs in top 10
Latency Metrics
Mean
336ms
7ms
Average response time
P50
248ms
7ms
50th percentile (median)
P90
305ms
7ms
90th percentile

Explore More

Compare more embeddings

See how all embedding models stack up. Compare OpenAI, Cohere, Jina AI, Voyage, and more. View comprehensive benchmarks, compare performance metrics, and find the perfect embedding for your RAG application.

View Full LeaderboardAll Leaderboards