OpenAI text-embedding-3-large
Supports 8,191 token context length with Matryoshka Representation Learning for flexible size reduction. Achieves 64.6% MTEB and 54.9% MIRACL benchmark scores, released January 2024. If you want to compare the best embedding models for your data, try Agentset.
Model Information
- Provider
- OpenAI
- License
- Proprietary
- Price per 1M tokens
- $0.130
- Dimensions
- 3072
- Release Date
- 2024-01-25
- Model Name
- text-embedding-3-large
- 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
OpenAI text-embedding-3-large's ELO performance varies across different benchmark datasets, showing its strengths in specific domains.
OpenAI text-embedding-3-large - 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
- 21ms
- P50 (Median)
- 21ms
- P90
- 21ms
DBPedia
Accuracy Metrics
- nDCG@5
- 0.815
- nDCG@10
- 0.795
- Recall@5
- 0.062
- Recall@10
- 0.123
Latency Distribution
- Mean
- 19ms
- P50 (Median)
- 19ms
- P90
- 19ms
FiQa
Accuracy Metrics
- nDCG@5
- 0.881
- nDCG@10
- 0.867
- Recall@5
- 0.701
- Recall@10
- 0.783
Latency Distribution
- Mean
- 13ms
- P50 (Median)
- 13ms
- P90
- 13ms
SciFact
Accuracy Metrics
- nDCG@5
- 0.702
- nDCG@10
- 0.727
- Recall@5
- 0.764
- Recall@10
- 0.861
Latency Distribution
- Mean
- 19ms
- P50 (Median)
- 19ms
- P90
- 19ms
MSMARCO
Accuracy Metrics
- nDCG@5
- 0.956
- nDCG@10
- 0.947
- Recall@5
- 0.123
- Recall@10
- 0.223
Latency Distribution
- Mean
- 28ms
- P50 (Median)
- 28ms
- P90
- 28ms
ARCD
Accuracy Metrics
- nDCG@5
- 0.829
- nDCG@10
- 0.829
- Recall@5
- 0.940
- Recall@10
- 0.940
Latency Distribution
- Mean
- 10ms
- P50 (Median)
- 10ms
- P90
- 10ms
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-large with other top embeddings to understand the differences in performance, accuracy, and latency.