Jina Embeddings v3 vs BAAI/bge-m3

Detailed comparison between Jina Embeddings v3 and BAAI/bge-m3. See which embedding best meets your accuracy and performance needs.

Model Comparison

Jina Embeddings v3 takes the lead.

Both Jina Embeddings v3 and BAAI/bge-m3 are powerful embedding models designed to improve retrieval quality in RAG applications. However, their performance characteristics differ in important ways.

Why Jina Embeddings v3:

  • Jina Embeddings v3 delivers better accuracy (nDCG@10: 0.766 vs 0.753)
  • BAAI/bge-m3 is 132889ms faster on average

Overview

Key metrics

ELO Rating

Overall ranking quality

Jina Embeddings v3

1491

BAAI/bge-m3

1491

Win Rate

Head-to-head performance

Jina Embeddings v3

40.3%

BAAI/bge-m3

40.9%

Accuracy (nDCG@10)

Ranking quality metric

Jina Embeddings v3

0.766

BAAI/bge-m3

0.753

Average Latency

Response time

Jina Embeddings v3

213763ms

BAAI/bge-m3

80874ms

Visual Performance Analysis

Performance

ELO Rating Comparison

Win/Loss/Tie Breakdown

Accuracy Across Datasets (nDCG@10)

Latency Distribution (ms)

Breakdown

How the models stack up

MetricJina Embeddings v3BAAI/bge-m3Description
Overall Performance
ELO Rating
1491
1491
Overall ranking quality based on pairwise comparisons
Win Rate
40.3%
40.9%
Percentage of comparisons won against other models
Pricing & Availability
Price per 1M tokens
$0.045
$0.010
Cost per million tokens processed
Release Date
2024-09-18
2024-01-27
Model release date
Accuracy Metrics
Avg nDCG@10
0.766
0.753
Normalized discounted cumulative gain at position 10
Performance Metrics
Avg Latency
213763ms
80874ms
Average response time across all datasets

Dataset Performance

By field

Comprehensive comparison of accuracy metrics (nDCG, Recall) and latency percentiles for each benchmark dataset.

PG

MetricJina Embeddings v3BAAI/bge-m3Description
Accuracy Metrics
Latency Metrics
Mean
155423ms
96375ms
Average response time
P50
152315ms
94448ms
50th percentile (median)
P90
178736ms
110831ms
90th percentile

business reports

MetricJina Embeddings v3BAAI/bge-m3Description
Accuracy Metrics
Latency Metrics
Mean
18149ms
24163ms
Average response time
P50
17786ms
23680ms
50th percentile (median)
P90
20871ms
27787ms
90th percentile

DBPedia

MetricJina Embeddings v3BAAI/bge-m3Description
Accuracy Metrics
nDCG@5
0.616
0.625
Ranking quality at top 5 results
nDCG@10
0.591
0.603
Ranking quality at top 10 results
Recall@5
0.225
0.236
% of relevant docs in top 5
Recall@10
0.340
0.341
% of relevant docs in top 10
Latency Metrics
Mean
199515ms
86619ms
Average response time
P50
195525ms
84887ms
50th percentile (median)
P90
229442ms
99612ms
90th percentile

FiQa

MetricJina Embeddings v3BAAI/bge-m3Description
Accuracy Metrics
nDCG@5
0.645
0.597
Ranking quality at top 5 results
nDCG@10
0.679
0.609
Ranking quality at top 10 results
Recall@5
0.633
0.607
% of relevant docs in top 5
Recall@10
0.741
0.666
% of relevant docs in top 10
Latency Metrics
Mean
458812ms
159871ms
Average response time
P50
449636ms
156674ms
50th percentile (median)
P90
527634ms
183852ms
90th percentile

SciFact

MetricJina Embeddings v3BAAI/bge-m3Description
Accuracy Metrics
nDCG@5
0.622
0.578
Ranking quality at top 5 results
nDCG@10
0.661
0.617
Ranking quality at top 10 results
Recall@5
0.695
0.652
% of relevant docs in top 5
Recall@10
0.800
0.763
% of relevant docs in top 10
Latency Metrics
Mean
270629ms
154804ms
Average response time
P50
265216ms
151708ms
50th percentile (median)
P90
311223ms
178025ms
90th percentile

MSMARCO

MetricJina Embeddings v3BAAI/bge-m3Description
Accuracy Metrics
nDCG@5
1.000
0.997
Ranking quality at top 5 results
nDCG@10
0.997
0.997
Ranking quality at top 10 results
Recall@5
0.123
0.122
% of relevant docs in top 5
Recall@10
0.220
0.220
% of relevant docs in top 10
Latency Metrics
Mean
476020ms
96153ms
Average response time
P50
466500ms
94230ms
50th percentile (median)
P90
547423ms
110576ms
90th percentile

NorQuAD

MetricJina Embeddings v3BAAI/bge-m3Description
Accuracy Metrics
Latency Metrics
Mean
45614ms
16285ms
Average response time
P50
44702ms
15959ms
50th percentile (median)
P90
52456ms
18728ms
90th percentile

ARCD

MetricJina Embeddings v3BAAI/bge-m3Description
Accuracy Metrics
nDCG@5
0.888
0.941
Ranking quality at top 5 results
nDCG@10
0.900
0.941
Ranking quality at top 10 results
Recall@5
0.920
0.960
% of relevant docs in top 5
Recall@10
0.960
0.960
% of relevant docs in top 10
Latency Metrics
Mean
85941ms
12723ms
Average response time
P50
84222ms
12469ms
50th percentile (median)
P90
98832ms
14631ms
90th percentile

Explore More

Compare more embeddings

See how all embedding models stack up. Compare OpenAI, Cohere, Jina AI, Voyage, and more. View comprehensive benchmarks, compare performance metrics, and find the perfect embedding for your RAG application.