Compare Embedding Models

Side-by-side comparison of embedding model specifications

	Jina Embeddings v3▾ 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 Jina Embeddings v5 Omni Small Jina Embeddings v5 Omni Nano Jina Embeddings v5 Omni Nano Text-Matching Jina Embeddings v5 Text Small Jina Embeddings v5 Text Nano Jina Embeddings v5 Text Small Text-Matching Jina Embeddings v3Jina AI	Jina Embeddings 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 Jina Embeddings v5 Omni Small Jina Embeddings v5 Omni Nano Jina Embeddings v5 Omni Nano Text-Matching Jina Embeddings v5 Text Small Jina Embeddings v5 Text Nano Jina Embeddings v5 Text Small Text-Matching Jina Embeddings v4Jina AI	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 Jina Embeddings v5 Omni Small Jina Embeddings v5 Omni Nano Jina Embeddings v5 Omni Nano Text-Matching Jina Embeddings v5 Text Small Jina Embeddings v5 Text Nano Jina Embeddings v5 Text Small Text-Matching Qwen3-Embedding-8BQwen	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 Jina Embeddings v5 Omni Small Jina Embeddings v5 Omni Nano Jina Embeddings v5 Omni Nano Text-Matching Jina Embeddings v5 Text Small Jina Embeddings v5 Text Nano Jina Embeddings v5 Text Small Text-Matching mxbai-embed-large-v1Mixedbread
SPECIFICATIONS
Max dimension	1K	2K	4K	1K
Max tokens	8K	33K	33K	512
Parameters	559M	3.8B	8B	335M
License	CC BY-NC 4.0	Apache 2.0	Apache 2.0	Apache 2.0
EMBEDDING TYPES
Types	Dense	DenseLate	Dense	Dense
MATRYOSHKA DIMENSIONS
Available sizes	32641282565121024	12825651210242048	3264128256512102420484096	641282565121024
INPUT MODALITIES
Text	✓	✓	✓	✓
Image	—	✓	—	—
PDF	—	✓	—	—
OUTPUT TYPES
Single vector	✓	✓	✓	✓
Multi vector	—	✓	—	—
LANGUAGE SUPPORT
Languages	🌍 89+	🌍 29+	🌍 100+	—
PRICING
Per 1M tokens	$0.020	$0.050	—	—
BENCHMARKS
CMTEB CHINESE	—	—	73.84	—
COIR	—	71.59	—	—
JINA VDR	—	84.11	—	—
LONGEMBED	55.66	67.11	—	—
MMTEB	58.58	66.49	—	—
MTEB AVG	—	—	—	64.68
MTEB EN	54.33	55.97	—	—
MTEB EN V2	—	—	75.22	—
MTEB MULTILINGUAL	—	—	70.58	—
MTEB RETRIEVAL	—	—	—	54.39
MTEB STS	—	—	—	85.00
VIDORE	—	90.17	—	—