Jina Embeddings v3
Built on XLM-RoBERTa with 570M parameters supporting 8,192 token context length across 89 languages. Features five task-specific LoRA adapters for retrieval, clustering, and classification with Matryoshka learning for flexible sizing. If you want to compare the best embedding models for your data, try Agentset.
Model Information
- Provider
- Jina AI
- License
- Open Source
- Price per 1M tokens
- $0.045
- Dimensions
- 1024
- Release Date
- 2024-09-18
- Model Name
- jina-embeddings-v3
- Total Evaluations
- 830
Performance Record
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
Performance Overview
ELO ratings by dataset
Jina Embeddings v3's ELO performance varies across different benchmark datasets, showing its strengths in specific domains.
Jina Embeddings v3 - ELO by Dataset
Detailed Metrics
Dataset breakdown
Performance metrics across different benchmark datasets, including accuracy and latency percentiles.
business reports
Accuracy Metrics
- nDCG@5
- 0.000
- nDCG@10
- 0.000
- Recall@5
- 0.000
- Recall@10
- 0.000
Latency Distribution
- Mean
- 26ms
- P50 (Median)
- 26ms
- P90
- 26ms
DBPedia
Accuracy Metrics
- nDCG@5
- 0.835
- nDCG@10
- 0.789
- Recall@5
- 0.062
- Recall@10
- 0.121
Latency Distribution
- Mean
- 107ms
- P50 (Median)
- 107ms
- P90
- 107ms
FiQa
Accuracy Metrics
- nDCG@5
- 0.764
- nDCG@10
- 0.775
- Recall@5
- 0.635
- Recall@10
- 0.745
Latency Distribution
- Mean
- 273ms
- P50 (Median)
- 273ms
- P90
- 273ms
SciFact
Accuracy Metrics
- nDCG@5
- 0.600
- nDCG@10
- 0.636
- Recall@5
- 0.709
- Recall@10
- 0.816
Latency Distribution
- Mean
- 75ms
- P50 (Median)
- 75ms
- P90
- 75ms
MSMARCO
Accuracy Metrics
- nDCG@5
- 0.958
- nDCG@10
- 0.944
- Recall@5
- 0.124
- Recall@10
- 0.219
Latency Distribution
- Mean
- 346ms
- P50 (Median)
- 346ms
- P90
- 346ms
ARCD
Accuracy Metrics
- nDCG@5
- 0.797
- nDCG@10
- 0.809
- Recall@5
- 0.920
- Recall@10
- 0.960
Latency Distribution
- Mean
- 513ms
- P50 (Median)
- 513ms
- P90
- 513ms
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 Jina Embeddings v3 with other top embeddings to understand the differences in performance, accuracy, and latency.