OpenAI text-embedding-3-small
Cost-efficient model at $0.02 per 1M tokens with 8,191 token context length. Features Matryoshka learning achieving 62.3% MTEB and 44.0% MIRACL scores for multilingual performance. If you want to compare the best embedding models for your data, try Agentset.
Model Information
- Provider
- OpenAI
- License
- Proprietary
- Price per 1M tokens
- $0.020
- Dimensions
- 1536
- Release Date
- 2024-01-25
- Model Name
- text-embedding-3-small
- Total Evaluations
- 829
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
OpenAI text-embedding-3-small's ELO performance varies across different benchmark datasets, showing its strengths in specific domains.
OpenAI text-embedding-3-small - 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
- 16ms
- P50 (Median)
- 16ms
- P90
- 16ms
DBPedia
Accuracy Metrics
- nDCG@5
- 0.858
- nDCG@10
- 0.807
- Recall@5
- 0.062
- Recall@10
- 0.123
Latency Distribution
- Mean
- 9ms
- P50 (Median)
- 9ms
- P90
- 9ms
FiQa
Accuracy Metrics
- nDCG@5
- 0.801
- nDCG@10
- 0.814
- Recall@5
- 0.624
- Recall@10
- 0.682
Latency Distribution
- Mean
- 16ms
- P50 (Median)
- 16ms
- P90
- 16ms
SciFact
Accuracy Metrics
- nDCG@5
- 0.663
- nDCG@10
- 0.684
- Recall@5
- 0.774
- Recall@10
- 0.840
Latency Distribution
- Mean
- 17ms
- P50 (Median)
- 17ms
- P90
- 17ms
MSMARCO
Accuracy Metrics
- nDCG@5
- 0.959
- nDCG@10
- 0.946
- Recall@5
- 0.122
- Recall@10
- 0.212
Latency Distribution
- Mean
- 20ms
- P50 (Median)
- 20ms
- P90
- 20ms
ARCD
Accuracy Metrics
- nDCG@5
- 0.786
- nDCG@10
- 0.793
- Recall@5
- 0.900
- Recall@10
- 0.920
Latency Distribution
- Mean
- 15ms
- P50 (Median)
- 15ms
- 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 OpenAI text-embedding-3-small with other top embeddings to understand the differences in performance, accuracy, and latency.