Embedding Model Rankings
Best Embedding Models
Text and multimodal embedding models ranked by the MTEB leaderboard: retrieval, classification, clustering, and STS.
Benchmark data last synced Sep 24, 2026
Filters
–
0+
–
27 models
| Compare | ||||||
|---|---|---|---|---|---|---|
AA74.7 | Alibaba | 65 | 1024 | 33K | 0.596B | |
AA72.7 | Microsoft | 62 | 1024 | 514 | 0.56B | |
AA72.6 | Microsoft | 66 | 640 | 33K | 0.268B | |
AA72.5 | Alibaba | 71 | 4096 | 33K | 7.6B | |
AA72.2 | Microsoft | 69 | 1024 | 33K | 0.596B | |
AA71.9 | 68 | 1024 | 33K | 0.596B | ||
AA71.9 | Alibaba | 70 | 2560 | 33K | 4B | |
BB68.7 | Jina AI | 67 | 768 | 8K | 0.212B | |
Ad CodeRabbitAI-powered Code Reviews. Cut review time & bugs in half, instantly.Try for Free | ||||||
BB64.1 | Octen AI | 69 | 4096 | 33K | 7.6B | |
BB60.3 | NVIDIA | 69 | 4096 | 33K | 7.5B | |
BB60.2 | Alibaba | 64 | 3584 | 33K | 7.1B | |
BB59.1 | Microsoft | 61 | 4096 | 33K | 7.1B | |
BB57.2 | 72 | 3840 | 33K | 11.8B | ||
BB56.6 | CodeFuse-AI (Ant Group) | 66 | 2048 | 41K | 1.7B | |
BB56.5 | Salesforce | 63 | 4096 | 33K | 7.1B | |
Rows per page
Page 1 of 2Related AI Model Tools
Model Providers
AI Models by Provider
Every AI lab that ships models we track, ranked by model count, average score, and frontier presence. Compare OpenAI, Anthropic, Meta, Google, Alibaba, and more.
Browse Providers
AI Model Families
Every model series we track, grouped by family. See every Llama, Qwen, GPT, Claude, Gemini, and beyond on a single page.
All AI Models
27
- BidirLM-1.7B-Embedding
- BidirLM-1B-Embedding
- BidirLM-Omni-2.5B-Embedding
- BOOM_4B_v1
- e5-mistral-7b-instruct
- F2LLM-v2-0.6B
- F2LLM-v2-14B
- F2LLM-v2-1.7B
- F2LLM-v2-4B
- F2LLM-v2-8B
- GritLM-7B
- GritLM-8x7B
- gte-Qwen2-7B-instruct
- harrier-oss-v1-0.6b
- harrier-oss-v1-270m
- harrier-oss-v1-27b
- jina-embeddings-v5-text-nano
- jina-embeddings-v5-text-small
- KaLM-Embedding-Gemma3-12B-2511
- Linq-Embed-Mistral
- llama-embed-nemotron-8b
- multilingual-e5-large-instruct
- Octen-Embedding-8B
- Qwen3-Embedding-0.6B
- Qwen3-Embedding-4B
- Qwen3-Embedding-8B
- SFR-Embedding-Mistral
Hardware Fit Guides
GPU Guides27
- GPUs for BidirLM-1.7B-Embedding
- GPUs for BidirLM-1B-Embedding
- GPUs for BidirLM-Omni-2.5B-Embedding
- GPUs for BOOM_4B_v1
- GPUs for e5-mistral-7b-instruct
- GPUs for F2LLM-v2-0.6B
- GPUs for F2LLM-v2-14B
- GPUs for F2LLM-v2-1.7B
- GPUs for F2LLM-v2-4B
- GPUs for F2LLM-v2-8B
- GPUs for GritLM-7B
- GPUs for GritLM-8x7B
- GPUs for gte-Qwen2-7B-instruct
- GPUs for harrier-oss-v1-0.6b
- GPUs for harrier-oss-v1-270m
- GPUs for harrier-oss-v1-27b
- GPUs for jina-embeddings-v5-text-nano
- GPUs for jina-embeddings-v5-text-small
- GPUs for KaLM-Embedding-Gemma3-12B-2511
- GPUs for Linq-Embed-Mistral
- GPUs for llama-embed-nemotron-8b
- GPUs for multilingual-e5-large-instruct
- GPUs for Octen-Embedding-8B
- GPUs for Qwen3-Embedding-0.6B
- GPUs for Qwen3-Embedding-4B
- GPUs for Qwen3-Embedding-8B
- GPUs for SFR-Embedding-Mistral