Compare Embeddings: GTE-Qwen2-7B-instruct, LFM2-ColBERT-350M, Voyage 3 Large, Voyage 3 Large

	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 GTE-Qwen2-7B-instructAlibaba	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	Voyage 3 Large▾ 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 Voyage 3 LargeVoyage AI	Voyage 3 Large▾ 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 Voyage 3 LargeVoyage AI
SPECIFICATIONS
Max dimension	4K	—	2K	2K
Max tokens	32K	—	32K	32K
Parameters	7B	350M	—	—
License	Apache 2.0	Apache 2.0	Proprietary	Proprietary
EMBEDDING TYPES
Types	Dense	LateColBERT	Dense	Dense
MATRYOSHKA DIMENSIONS
Available sizes	—	—	25651210242048	25651210242048
INPUT MODALITIES
Text	✓	✓	✓	✓
Image	—	—	—	—
PDF	—	—	—	—
OUTPUT TYPES
Single vector	✓	—	✓	✓
Multi vector	—	✓	—	—
LANGUAGE SUPPORT
Languages	🌍 Multi	🌍 Multi	🌍 Multi	🌍 Multi
PRICING
Per 1M tokens	—	—	—	—
BENCHMARKS
CMTEB 35	72.05	—	—	—
MTEB 56	70.24	—	—	—
MTEB FR	68.25	—	—	—
MTEB PL	67.86	—	—	—

Compare Embedding Models