Compare Embeddings: GTE-Qwen2-7B-instruct, Qwen3-Embedding-8B, Cohere Embed English v3, Qwen3-Embedding-8B

	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	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	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 Cohere Embed English v3Cohere	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
SPECIFICATIONS
Max dimension	4K	4K	1K	4K
Max tokens	32K	33K	512	33K
Parameters	7B	8B	—	8B
License	Apache 2.0	Apache 2.0	Proprietary	Apache 2.0
EMBEDDING TYPES
Types	Dense	Dense	Dense	Dense
MATRYOSHKA DIMENSIONS
Available sizes	—	3264128256512102420484096	—	3264128256512102420484096
INPUT MODALITIES
Text	✓	✓	✓	✓
Image	—	—	✓	—
PDF	—	—	—	—
OUTPUT TYPES
Single vector	✓	✓	✓	✓
Multi vector	—	—	—	—
LANGUAGE SUPPORT
Languages	🌍 Multi	🌍 100+	—	🌍 100+
PRICING
Per 1M tokens	—	—	—	—
BENCHMARKS
CMTEB 35	72.05	—	—	—
CMTEB CHINESE	—	73.84	—	73.84
MTEB 56	70.24	—	—	—
MTEB AVG	—	—	64.47	—
MTEB EN V2	—	75.22	—	75.22
MTEB FR	68.25	—	—	—
MTEB MULTILINGUAL	—	70.58	—	70.58
MTEB PL	67.86	—	—	—
MTEB RETRIEVAL	—	—	55.00	—

Compare Embedding Models