Compare Embeddings: Qwen3-Embedding-8B, LFM2-ColBERT-350M, Qwen3-Embedding-8B, Jina Embeddings v3

	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	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	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	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 v3Jina AI
SPECIFICATIONS
Max dimension	4K	—	4K	1K
Max tokens	33K	—	33K	8K
Parameters	8B	350M	8B	559M
License	Apache 2.0	Apache 2.0	Apache 2.0	CC BY-NC 4.0
EMBEDDING TYPES
Types	Dense	LateColBERT	Dense	Dense
MATRYOSHKA DIMENSIONS
Available sizes	3264128256512102420484096	—	3264128256512102420484096	32641282565121024
INPUT MODALITIES
Text	✓	✓	✓	✓
Image	—	—	—	—
PDF	—	—	—	—
OUTPUT TYPES
Single vector	✓	—	✓	✓
Multi vector	—	✓	—	—
LANGUAGE SUPPORT
Languages	🌍 100+	🌍 Multi	🌍 100+	🌍 89+
PRICING
Per 1M tokens	—	—	—	$0.020
BENCHMARKS
CMTEB CHINESE	73.84	—	73.84	—
LONGEMBED	—	—	—	55.66
MMTEB	—	—	—	58.58
MTEB EN	—	—	—	54.33
MTEB EN V2	75.22	—	75.22	—
MTEB MULTILINGUAL	70.58	—	70.58	—

Compare Embedding Models