← Back to Models

Compare Embedding Models

Side-by-side comparison of embedding model specifications

Linq-Embed-Mistral▾
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
Linq-Embed-MistralLinq AI
mxbai-embed-large-v1▾
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
mxbai-embed-large-v1Mixedbread
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
LFM2-ColBERT-350M▾
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
LFM2-ColBERT-350MLiquid AI
SPECIFICATIONS
Max dimension 4K 1K 2K —
Max tokens 4K 512 128K —
Parameters 7B 335M — 350M
License Apache 2.0 Apache 2.0 Proprietary Apache 2.0
EMBEDDING TYPES
Types
Dense
Dense
Dense
LateColBERT
MATRYOSHKA DIMENSIONS
Available sizes —
641282565121024
25651210241536
—
INPUT MODALITIES
Text ✓ ✓ ✓ ✓
Image — — ✓ —
PDF — — ✓ —
OUTPUT TYPES
Single vector ✓ ✓ ✓ —
Multi vector — — — ✓
LANGUAGE SUPPORT
Languages 🌍 Multi — 🌍 100+ 🌍 Multi
PRICING
Per 1M tokens — — — —
BENCHMARKS
MTEB AVG 68.20 64.68 — —
MTEB RETRIEVAL 60.20 54.39 — —
MTEB STS — 85.00 — —