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
#13
of 14
ELO Rating
1478
#13
Win Rate
37.3%
#13
Accuracy (nDCG@10)
0.751
#12
Latency
22ms
#9

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
1919

Performance Record

Wins715 (37.3%)
Losses986 (51.4%)
Ties218 (11.4%)
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 150150.0% WR120W-117L-3T

Latency Distribution

Mean
22ms
P50 (Median)
21ms
P90
25ms

ARCD

ELO 149636.3% WR87W-95L-58T

Accuracy Metrics

nDCG@5
0.865
nDCG@10
0.872
Recall@5
0.880
Recall@10
0.900

Latency Distribution

Mean
23ms
P50 (Median)
23ms
P90
27ms

PG

ELO 149449.2% WR118W-120L-2T

Latency Distribution

Mean
13ms
P50 (Median)
13ms
P90
15ms

SciFact

ELO 148845.0% WR108W-128L-4T

Accuracy Metrics

nDCG@5
0.666
nDCG@10
0.686
Recall@5
0.723
Recall@10
0.783

Latency Distribution

Mean
20ms
P50 (Median)
19ms
P90
23ms

NorQuAD

ELO 147918.3% WR44W-79L-117T

Latency Distribution

Mean
32ms
P50 (Median)
31ms
P90
36ms

FiQa

ELO 146538.3% WR92W-146L-2T

Accuracy Metrics

nDCG@5
0.620
nDCG@10
0.647
Recall@5
0.590
Recall@10
0.680

Latency Distribution

Mean
42ms
P50 (Median)
41ms
P90
49ms

MSMARCO

ELO 146232.9% WR79W-140L-21T

Accuracy Metrics

nDCG@5
0.997
nDCG@10
0.992
Recall@5
0.122
Recall@10
0.215

Latency Distribution

Mean
13ms
P50 (Median)
13ms
P90
15ms

DBPedia

ELO 144328.0% WR67W-161L-11T

Accuracy Metrics

nDCG@5
0.549
nDCG@10
0.556
Recall@5
0.216
Recall@10
0.350

Latency Distribution

Mean
13ms
P50 (Median)
13ms
P90
15ms

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.