Back to all embeddings

Voyage 3.5

Distilled from voyage-3-large for cost efficiency with flexible sizing options. Achieves 99% vector database cost reduction through binary quantization while maintaining strong retrieval quality. If you want to compare the best embedding models for your data, try Agentset.

Leaderboard Rank
#10
of 18
ELO Rating
1489
#10
Win Rate
47.0%
#9
Accuracy (nDCG@10)
0.703
#4
Latency
18ms
#5

Model Information

Provider
Voyage AI
License
Proprietary
Price per 1M tokens
$0.060
Dimensions
1024
Release Date
2025-05-20
Model Name
voyage-3.5
Total Evaluations
830

Performance Record

Wins390 (47.0%)
Losses393 (47.3%)
Ties47 (5.7%)
Wins
Losses
Ties

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.

Trusted by teams building production RAG applications

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

Performance Overview

ELO ratings by dataset

Voyage 3.5's ELO performance varies across different benchmark datasets, showing its strengths in specific domains.

Voyage 3.5 - ELO by Dataset

Detailed Metrics

Dataset breakdown

Performance metrics across different benchmark datasets, including accuracy and latency percentiles.

business reports

ELO 150050.0% WR80W-75L-5T

Accuracy Metrics

nDCG@5
0.000
nDCG@10
0.000
Recall@5
0.000
Recall@10
0.000

Latency Distribution

Mean
16ms
P50 (Median)
16ms
P90
16ms

DBPedia

ELO 150042.5% WR68W-79L-13T

Accuracy Metrics

nDCG@5
0.783
nDCG@10
0.782
Recall@5
0.062
Recall@10
0.121

Latency Distribution

Mean
7ms
P50 (Median)
7ms
P90
7ms

FiQa

ELO 150049.3% WR74W-72L-4T

Accuracy Metrics

nDCG@5
0.848
nDCG@10
0.825
Recall@5
0.688
Recall@10
0.783

Latency Distribution

Mean
63ms
P50 (Median)
63ms
P90
63ms

SciFact

ELO 150035.6% WR57W-102L-1T

Accuracy Metrics

nDCG@5
0.669
nDCG@10
0.705
Recall@5
0.733
Recall@10
0.840

Latency Distribution

Mean
7ms
P50 (Median)
7ms
P90
7ms

MSMARCO

ELO 150055.6% WR89W-49L-22T

Accuracy Metrics

nDCG@5
0.958
nDCG@10
0.944
Recall@5
0.122
Recall@10
0.221

Latency Distribution

Mean
6ms
P50 (Median)
6ms
P90
6ms

ARCD

ELO 150055.0% WR22W-16L-2T

Accuracy Metrics

nDCG@5
0.867
nDCG@10
0.873
Recall@5
0.960
Recall@10
0.980

Latency Distribution

Mean
8ms
P50 (Median)
8ms
P90
8ms

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.

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);
}

Compare Models

See how it stacks up

Compare Voyage 3.5 with other top embeddings to understand the differences in performance, accuracy, and latency.