📐
LEADERBOARD
Embedding Models
Models that convert text to vector representations for similarity search
15tools ranked
Embedding Models Rankings
Ranked by overall ToolRoute Score across all benchmark dimensions
| Rank | Tool Name | ToolRoute Score | Output | Reliability | Efficiency | Cost | Trust | Stars |
|---|---|---|---|---|---|---|---|---|
| 🥇 | OpenAI text-embedding-3Official | 7.0 | 7.0 | 7.1 | 6.9 | 6.0 | 9.0 | 31,612 |
| 🥈 | BGE-Large | 6.9 | 6.7 | 6.6 | 6.8 | 7.2 | 8.5 | 12,152 |
| 🥉 | E5-Mistral | 6.9 | 6.8 | 6.6 | 6.7 | 7.1 | 8.5 | 22,208 |
| #4 | Cohere Embed v3Official | 6.9 | 6.9 | 6.9 | 6.8 | 5.7 | 8.7 | 399 |
| #5 | Snowflake Arctic EmbedOfficial | 6.7 | 6.7 | 6.7 | 6.9 | 6.9 | 6.8 | 3,000 |
| #6 | Jina Embeddings v3 | 6.7 | 6.8 | 6.7 | 6.9 | 6.5 | 7.0 | 21,860 |
| #7 | Stella Embed | 6.7 | 6.7 | 6.5 | 6.8 | 7.2 | 6.5 | 63 |
| #8 | MxBai Embed | 6.7 | 6.6 | 6.5 | 7.1 | 7.2 | 6.4 | 1,800 |
| #9 | Mixedbread Embed | 6.7 | 6.7 | 6.6 | 6.8 | 7.0 | 6.5 | 2,000 |
| #10 | Voyage AI 3Official | 6.7 | 6.9 | 6.8 | 6.7 | 5.5 | 7.5 | 112 |
| #11 | GTE-Qwen2 | 6.7 | 6.6 | 6.5 | 6.9 | 7.2 | 6.5 | 27,602 |
| #12 | Nomic Embed | 6.6 | 6.6 | 6.5 | 7.0 | 7.2 | 6.0 | 1,880 |
| #13 | Instructor XL | 6.6 | 6.6 | 6.4 | 6.7 | 7.2 | 6.5 | 2,022 |
| #14 | Amazon Titan EmbedOfficial | 6.5 | 6.4 | 6.6 | 6.7 | 6.0 | 6.9 | 5,000 |
| #15 | Google GeckoOfficial | 6.3 | 6.5 | 6.7 | 7.1 | 6.2 | 3.5 | 2,327 |
💡
Why OpenAI text-embedding-3 is #1
OpenAI text-embedding-3 leads BGE-Large by +0.5 in Reliability, and also wins in Trust, Output Quality, Efficiency.
Output Quality
7.0
vs 6.7
Reliability
7.1
vs 6.6
Efficiency
6.9
vs 6.8
Cost
6.0
vs 7.2
Trust
9.0
vs 8.5
Score Guide:9+ Exceptional8+ Excellent7+ Good6+ Fair<6 Below Avg
Contribute Benchmark Data
Help improve these rankings by submitting real-world telemetry. Contributors earn routing credits for every data point.