← Back to Models

Compare Embedding Models

Side-by-side comparison of embedding model specifications

Cohere Embed v4▾
Jina Embeddings v4 Jina Embeddings v3 Qwen3-Embedding-8B Gemini Embedding 001 mxbai-embed-large-v1✓ Cohere Embed v4 Cohere Embed English v3 Cohere Embed Multilingual v3 Voyage 3 Large GTE-Qwen2-7B-instruct Linq-Embed-Mistral LFM2-ColBERT-350M
Cohere Embed v4Cohere
Qwen3-Embedding-8B▾
Jina Embeddings v4 Jina Embeddings v3✓ Qwen3-Embedding-8B Gemini Embedding 001 mxbai-embed-large-v1 Cohere Embed v4 Cohere Embed English v3 Cohere Embed Multilingual v3 Voyage 3 Large GTE-Qwen2-7B-instruct Linq-Embed-Mistral LFM2-ColBERT-350M
Qwen3-Embedding-8BQwen
+Add
SPECIFICATIONS
Max dimension 2K 4K
Max tokens 128K 33K
Parameters — 8B
License Proprietary Apache 2.0
EMBEDDING TYPES
Types
Dense
Dense
MATRYOSHKA DIMENSIONS
Available sizes
25651210241536
3264128256512102420484096
INPUT MODALITIES
Text ✓ ✓
Image ✓ —
PDF ✓ —
OUTPUT TYPES
Single vector ✓ ✓
Multi vector — —
LANGUAGE SUPPORT
Languages 🌍 100+ 🌍 100+
PRICING
Per 1M tokens — —
BENCHMARKS
CMTEB CHINESE — 73.84
MTEB EN V2 — 75.22
MTEB MULTILINGUAL — 70.58