Voyage 4
Mid-sized model approaching the retrieval quality of voyage-3-large while maintaining mid-tier model efficiency. Part of shared embedding space with Voyage 4 family, enabling asymmetric retrieval. Supports Matryoshka learning (2048/1024/512/256 dims) and multiple quantization options.
Model Information
- Provider
- Voyage AI
- License
- Proprietary
- Price per 1M tokens
- $0.060
- Dimensions
- 1024
- Release Date
- 2026-01-15
- Model Name
- voyage-4
- Total Evaluations
- 780
Performance Record
Wins481 (61.7%)
Losses235 (30.1%)
Ties64 (8.2%)
Wins
Losses
Ties
Performance Overview
ELO ratings by dataset
Voyage 4's ELO performance varies across different benchmark datasets, showing its strengths in specific domains.
Voyage 4 - ELO by Dataset
Detailed Metrics
Dataset breakdown
Performance metrics across different benchmark datasets, including accuracy and latency percentiles.
DBPedia
ELO 162563.1% WR82W-37L-11T
Accuracy Metrics
- nDCG@5
- 0.815
- nDCG@10
- 0.811
- Recall@5
- 0.062
- Recall@10
- 0.122
Latency Distribution
- Mean
- 13ms
- P50 (Median)
- 13ms
- P90
- 15ms
business reports
ELO 161364.6% WR84W-43L-3T
Latency Distribution
- Mean
- 15ms
- P50 (Median)
- 15ms
- P90
- 17ms
PG
ELO 15000.0% WR0W-0L-10T
Latency Distribution
- Mean
- 17ms
- P50 (Median)
- 17ms
- P90
- 19ms
FiQa
ELO 15000.0% WR0W-0L-10T
Accuracy Metrics
- nDCG@5
- 0.873
- nDCG@10
- 0.859
- Recall@5
- 0.763
- Recall@10
- 0.840
Latency Distribution
- Mean
- 14ms
- P50 (Median)
- 14ms
- P90
- 15ms
MSMARCO
ELO 15000.0% WR0W-0L-10T
Accuracy Metrics
- nDCG@5
- 0.941
- nDCG@10
- 0.931
- Recall@5
- 0.123
- Recall@10
- 0.221
Latency Distribution
- Mean
- 13ms
- P50 (Median)
- 13ms
- P90
- 14ms
ARCD
ELO 15000.0% WR0W-0L-0T
Accuracy Metrics
- nDCG@5
- 0.936
- nDCG@10
- 0.936
- Recall@5
- 1.000
- Recall@10
- 1.000
Latency Distribution
- Mean
- 28ms
- P50 (Median)
- 28ms
- P90
- 30ms
SciFact
ELO 14650.0% WR0W-1L-9T
Accuracy Metrics
- nDCG@5
- 0.737
- nDCG@10
- 0.758
- Recall@5
- 0.804
- Recall@10
- 0.878
Latency Distribution
- Mean
- 16ms
- P50 (Median)
- 16ms
- P90
- 18ms
Compare Models
See how it stacks up
Compare Voyage 4 with other top embeddings to understand the differences in performance, accuracy, and latency.