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.
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
- 1920
Performance Record
Wins856 (44.6%)
Losses811 (42.2%)
Ties253 (13.2%)
Wins
Losses
Ties
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.
PG
ELO 152557.9% WR139W-99L-2T
Latency Distribution
- Mean
- 9ms
- P50 (Median)
- 9ms
- P90
- 11ms
business reports
ELO 152254.6% WR131W-98L-11T
Latency Distribution
- Mean
- 7ms
- P50 (Median)
- 7ms
- P90
- 8ms
NorQuAD
ELO 151729.6% WR71W-46L-123T
Latency Distribution
- Mean
- 16ms
- P50 (Median)
- 15ms
- P90
- 18ms
MSMARCO
ELO 150044.6% WR107W-106L-27T
Accuracy Metrics
- nDCG@5
- 0.997
- nDCG@10
- 0.990
- Recall@5
- 0.122
- Recall@10
- 0.213
Latency Distribution
- Mean
- 7ms
- P50 (Median)
- 7ms
- P90
- 8ms
SciFact
ELO 149547.9% WR115W-122L-3T
Accuracy Metrics
- nDCG@5
- 0.682
- nDCG@10
- 0.707
- Recall@5
- 0.778
- Recall@10
- 0.843
Latency Distribution
- Mean
- 11ms
- P50 (Median)
- 11ms
- P90
- 13ms
DBPedia
ELO 149245.8% WR110W-119L-11T
Accuracy Metrics
- nDCG@5
- 0.605
- nDCG@10
- 0.604
- Recall@5
- 0.230
- Recall@10
- 0.365
Latency Distribution
- Mean
- 7ms
- P50 (Median)
- 7ms
- P90
- 8ms
FiQa
ELO 148845.0% WR108W-126L-6T
Accuracy Metrics
- nDCG@5
- 0.635
- nDCG@10
- 0.647
- Recall@5
- 0.623
- Recall@10
- 0.681
Latency Distribution
- Mean
- 8ms
- P50 (Median)
- 8ms
- P90
- 9ms
ARCD
ELO 148731.3% WR75W-95L-70T
Accuracy Metrics
- nDCG@5
- 0.855
- nDCG@10
- 0.862
- Recall@5
- 0.900
- Recall@10
- 0.920
Latency Distribution
- Mean
- 11ms
- P50 (Median)
- 10ms
- P90
- 12ms
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.