OpenAI text-embedding-3-small vs Voyage 3.5 Lite

Detailed comparison between OpenAI text-embedding-3-small and Voyage 3.5 Lite. See which embedding best meets your accuracy and performance needs.

Model Comparison

Voyage 3.5 Lite takes the lead.

Both OpenAI text-embedding-3-small and Voyage 3.5 Lite are powerful embedding models designed to improve retrieval quality in RAG applications. However, their performance characteristics differ in important ways.

Why Voyage 3.5 Lite:

  • Voyage 3.5 Lite delivers better accuracy (nDCG@10: 0.803 vs 0.762)
  • OpenAI text-embedding-3-small is 6178ms faster on average

Overview

Key metrics

ELO Rating

Overall ranking quality

OpenAI text-embedding-3-small

1503

Voyage 3.5 Lite

1503

Win Rate

Head-to-head performance

OpenAI text-embedding-3-small

44.6%

Voyage 3.5 Lite

44.4%

Accuracy (nDCG@10)

Ranking quality metric

OpenAI text-embedding-3-small

0.762

Voyage 3.5 Lite

0.803

Average Latency

Response time

OpenAI text-embedding-3-small

29958ms

Voyage 3.5 Lite

36136ms

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

MetricOpenAI text-embedding-3-smallVoyage 3.5 LiteDescription
Overall Performance
ELO Rating
1503
1503
Overall ranking quality based on pairwise comparisons
Win Rate
44.6%
44.4%
Percentage of comparisons won against other models
Pricing & Availability
Price per 1M tokens
$0.020
$0.020
Cost per million tokens processed
Release Date
2024-01-25
2025-05-20
Model release date
Accuracy Metrics
Avg nDCG@10
0.762
0.803
Normalized discounted cumulative gain at position 10
Performance Metrics
Avg Latency
29958ms
36136ms
Average response time across all datasets

Dataset Performance

By field

Comprehensive comparison of accuracy metrics (nDCG, Recall) and latency percentiles for each benchmark dataset.

PG

MetricOpenAI text-embedding-3-smallVoyage 3.5 LiteDescription
Accuracy Metrics
Latency Metrics
Mean
55877ms
47120ms
Average response time
P50
54759ms
46178ms
50th percentile (median)
P90
64259ms
54188ms
90th percentile

business reports

MetricOpenAI text-embedding-3-smallVoyage 3.5 LiteDescription
Accuracy Metrics
Latency Metrics
Mean
5645ms
5629ms
Average response time
P50
5532ms
5516ms
50th percentile (median)
P90
6492ms
6473ms
90th percentile

DBPedia

MetricOpenAI text-embedding-3-smallVoyage 3.5 LiteDescription
Accuracy Metrics
nDCG@5
0.605
0.641
Ranking quality at top 5 results
nDCG@10
0.604
0.632
Ranking quality at top 10 results
Recall@5
0.230
0.219
% of relevant docs in top 5
Recall@10
0.365
0.367
% of relevant docs in top 10
Latency Metrics
Mean
35365ms
32706ms
Average response time
P50
34658ms
32052ms
50th percentile (median)
P90
40670ms
37612ms
90th percentile

FiQa

MetricOpenAI text-embedding-3-smallVoyage 3.5 LiteDescription
Accuracy Metrics
nDCG@5
0.635
0.708
Ranking quality at top 5 results
nDCG@10
0.647
0.736
Ranking quality at top 10 results
Recall@5
0.623
0.687
% of relevant docs in top 5
Recall@10
0.681
0.780
% of relevant docs in top 10
Latency Metrics
Mean
41338ms
85143ms
Average response time
P50
40511ms
83440ms
50th percentile (median)
P90
47539ms
97914ms
90th percentile

SciFact

MetricOpenAI text-embedding-3-smallVoyage 3.5 LiteDescription
Accuracy Metrics
nDCG@5
0.682
0.670
Ranking quality at top 5 results
nDCG@10
0.707
0.719
Ranking quality at top 10 results
Recall@5
0.778
0.718
% of relevant docs in top 5
Recall@10
0.843
0.843
% of relevant docs in top 10
Latency Metrics
Mean
55544ms
58245ms
Average response time
P50
54433ms
57080ms
50th percentile (median)
P90
63876ms
66982ms
90th percentile

MSMARCO

MetricOpenAI text-embedding-3-smallVoyage 3.5 LiteDescription
Accuracy Metrics
nDCG@5
0.997
0.994
Ranking quality at top 5 results
nDCG@10
0.990
0.995
Ranking quality at top 10 results
Recall@5
0.122
0.122
% of relevant docs in top 5
Recall@10
0.213
0.222
% of relevant docs in top 10
Latency Metrics
Mean
35961ms
49482ms
Average response time
P50
35242ms
48492ms
50th percentile (median)
P90
41355ms
56904ms
90th percentile

NorQuAD

MetricOpenAI text-embedding-3-smallVoyage 3.5 LiteDescription
Accuracy Metrics
Latency Metrics
Mean
6467ms
7081ms
Average response time
P50
6338ms
6939ms
50th percentile (median)
P90
7437ms
8143ms
90th percentile

ARCD

MetricOpenAI text-embedding-3-smallVoyage 3.5 LiteDescription
Accuracy Metrics
nDCG@5
0.855
0.928
Ranking quality at top 5 results
nDCG@10
0.862
0.935
Ranking quality at top 10 results
Recall@5
0.900
0.960
% of relevant docs in top 5
Recall@10
0.920
0.980
% of relevant docs in top 10
Latency Metrics
Mean
3464ms
3679ms
Average response time
P50
3395ms
3605ms
50th percentile (median)
P90
3984ms
4231ms
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.