Compare Embeddings: Qwen3-Embedding-8B, Qwen3-Embedding-8B, GTE-Qwen2-7B-instruct, Cohere Embed v4

	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	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	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	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 Cohere Embed v4Cohere
SPECIFICATIONS
Max dimension	4K	4K	4K	2K
Max tokens	33K	33K	32K	128K
Parameters	8B	8B	7B	—
License	Apache 2.0	Apache 2.0	Apache 2.0	Proprietary
EMBEDDING TYPES
Types	Dense	Dense	Dense	Dense
MATRYOSHKA DIMENSIONS
Available sizes	3264128256512102420484096	3264128256512102420484096	—	25651210241536
INPUT MODALITIES
Text	✓	✓	✓	✓
Image	—	—	—	✓
PDF	—	—	—	✓
OUTPUT TYPES
Single vector	✓	✓	✓	✓
Multi vector	—	—	—	—
LANGUAGE SUPPORT
Languages	🌍 100+	🌍 100+	🌍 Multi	🌍 100+
PRICING
Per 1M tokens	—	—	—	—
BENCHMARKS
CMTEB 35	—	—	72.05	—
CMTEB CHINESE	73.84	73.84	—	—
MTEB 56	—	—	70.24	—
MTEB EN V2	75.22	75.22	—	—
MTEB FR	—	—	68.25	—
MTEB MULTILINGUAL	70.58	70.58	—	—
MTEB PL	—	—	67.86	—

Compare Embedding Models