Compare Embedding Models

Side-by-side comparison of embedding model specifications

	Jina Embeddings v5 Text Nano▾ 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 v5 Text NanoJina AI	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 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 Cohere Embed v4Cohere	Cohere Embed English 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 Cohere Embed English v3Cohere	GTE-Qwen2-7B-instruct▾ 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 GTE-Qwen2-7B-instructAlibaba
SPECIFICATIONS
Max dimension	768	2K	1K	4K
Max tokens	8K	128K	512	32K
Parameters	239M	—	—	7B
License	CC BY-NC 4.0	Proprietary	Proprietary	Apache 2.0
EMBEDDING TYPES
Types	Dense	Dense	Dense	Dense
MATRYOSHKA DIMENSIONS
Available sizes	3264128256512768	25651210241536	—	—
INPUT MODALITIES
Text	✓	✓	✓	✓
Image	—	✓	✓	—
PDF	—	✓	—	—
OUTPUT TYPES
Single vector	—	✓	✓	✓
Multi vector	—	—	—	—
LANGUAGE SUPPORT
Languages	—	🌍 100+	—	🌍 Multi
PRICING
Per 1M tokens	—	—	—	—
BENCHMARKS
CMTEB 35	—	—	—	72.05
MMTEB	65.50	—	—	—
MTEB 56	—	—	—	70.24
MTEB AVG	—	—	64.47	—
MTEB ENGLISH V2	71.00	—	—	—
MTEB FR	—	—	—	68.25
MTEB PL	—	—	—	67.86
MTEB RETRIEVAL	—	—	55.00	—