Back to all embeddings

Qwen3 Embedding 0.6B

Lightweight 600M parameter model supporting 100+ natural and programming languages for efficient processing. Optimized for high-volume applications including code retrieval, text classification, clustering, and bitext mining. If you want to compare the best embedding models for your data, try Agentset.

Leaderboard Rank
#16
of 18
ELO Rating
1420
#16
Win Rate
35.7%
#15
Accuracy (nDCG@10)
0.656
#10
Latency
25ms
#8

Model Information

Provider
Qwen
License
Open Source
Price per 1M tokens
$0.010
Dimensions
1024
Release Date
2025-06-06
Model Name
qwen3-embedding-0.6b
Total Evaluations
830

Performance Record

Wins296 (35.7%)
Losses492 (59.3%)
Ties42 (5.1%)
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

Qwen3 Embedding 0.6B's ELO performance varies across different benchmark datasets, showing its strengths in specific domains.

Qwen3 Embedding 0.6B - ELO by Dataset

Detailed Metrics

Dataset breakdown

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

business reports

ELO 150049.4% WR79W-76L-5T

Accuracy Metrics

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

Latency Distribution

Mean
21ms
P50 (Median)
21ms
P90
21ms

DBPedia

ELO 150020.0% WR32W-119L-9T

Accuracy Metrics

nDCG@5
0.716
nDCG@10
0.730
Recall@5
0.053
Recall@10
0.105

Latency Distribution

Mean
13ms
P50 (Median)
13ms
P90
13ms

FiQa

ELO 150024.7% WR37W-110L-3T

Accuracy Metrics

nDCG@5
0.755
nDCG@10
0.755
Recall@5
0.591
Recall@10
0.683

Latency Distribution

Mean
19ms
P50 (Median)
19ms
P90
19ms

SciFact

ELO 150055.6% WR89W-67L-4T

Accuracy Metrics

nDCG@5
0.658
nDCG@10
0.666
Recall@5
0.718
Recall@10
0.779

Latency Distribution

Mean
62ms
P50 (Median)
62ms
P90
62ms

MSMARCO

ELO 150027.5% WR44W-101L-15T

Accuracy Metrics

nDCG@5
0.943
nDCG@10
0.933
Recall@5
0.122
Recall@10
0.215

Latency Distribution

Mean
15ms
P50 (Median)
15ms
P90
15ms

ARCD

ELO 150037.5% WR15W-19L-6T

Accuracy Metrics

nDCG@5
0.757
nDCG@10
0.763
Recall@5
0.880
Recall@10
0.900

Latency Distribution

Mean
18ms
P50 (Median)
18ms
P90
18ms

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 Qwen3 Embedding 0.6B with other top embeddings to understand the differences in performance, accuracy, and latency.