model_meta: sentence-transformers/all-MiniLM-L6-v2: link: https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2 revision: 8b3219a92973c328a8e22fadcfa821b5dc75636a desc: all-MiniLM-L6-v2 by Sentence Transformers seq_len: 512 size: 23 dim: 384 license: Apache 2.0 organization: Sentence Transformers mteb_overall: 56.26 mteb_retrieval: 41.95 mteb_sts: 78.90 mteb_clustering: 42.35 intfloat/multilingual-e5-small: link: https://huggingface.co/intfloat/multilingual-e5-small revision: e4ce9877abf3edfe10b0d82785e83bdcb973e22e desc: multilingual-e5-small by Microsoft seq_len: 512 size: 44 dim: 384 license: MIT License organization: Microsoft mteb_overall: 57.87 mteb_retrieval: 46.64 mteb_sts: 79.10 mteb_clustering: 37.08 intfloat/multilingual-e5-large-instruct: link: https://huggingface.co/intfloat/multilingual-e5-large-instruct revision: baa7be480a7de1539afce709c8f13f833a510e0a desc: multilingual-e5-large-instruct by Microsoft seq_len: 514 size: 560 dim: 1024 license: MIT License organization: Microsoft instruction_query_arxiv: Given a query, retrieve a relevant paper title and abstract from arXiv instruction_query_wikipedia: Given a query, retrieve a relevant title and passage from Wikipedia instruction_query_stackexchange: Given a query, retrieve a relevant question and answer from Stack Exchange instruction_sts: Retrieve semantically similar text instruction_clustering: Identify the topic/theme/category of the text mteb_overall: 64.41 mteb_retrieval: 52.47 mteb_sts: 84.78 mteb_clustering: 47.10 intfloat/e5-mistral-7b-instruct: link: https://huggingface.co/intfloat/e5-mistral-7b-instruct revision: 07163b72af1488142a360786df853f237b1a3ca1 desc: e5-mistral-7b-instruct by Microsoft seq_len: 32768 size: 7111 dim: 4096 license: MIT License organization: Microsoft instruction_query_arxiv: Given a query, retrieve a relevant paper title and abstract from arXiv instruction_query_wikipedia: Given a query, retrieve a relevant title and passage from Wikipedia instruction_query_stackexchange: Given a query, retrieve a relevant question and answer from Stack Exchange instruction_sts: Retrieve semantically similar text instruction_clustering: Identify the topic/theme/category of the text mteb_overall: 66.63 mteb_retrieval: 56.89 mteb_sts: 84.63 mteb_clustering: 50.26 GritLM/GritLM-7B: link: https://huggingface.co/GritLM/GritLM-7B revision: 13f00a0e36500c80ce12870ea513846a066004af desc: GritLM-7B by Contextual AI, HKU, Microsoft seq_len: 32768 size: 7240 dim: 4096 license: Apache 2.0 organization: Contextual AI, HKU, Microsoft instruction_query_arxiv: Given a query, retrieve a relevant paper title and abstract from arXiv instruction_query_wikipedia: Given a query, retrieve a relevant title and passage from Wikipedia instruction_query_stackexchange: Given a query, retrieve a relevant question and answer from Stack Exchange instruction_sts: Retrieve semantically similar text instruction_clustering: Identify the topic/theme/category of the text mteb_overall: 66.76 mteb_retrieval: 57.41 mteb_sts: 83.35 mteb_clustering: 50.61 BAAI/bge-large-en-v1.5: link: https://huggingface.co/BAAI/bge-large-en-v1.5 revision: d4aa6901d3a41ba39fb536a557fa166f842b0e09 desc: bge-large-en-v1.5 by BAAI seq_len: 512 size: 335 dim: 1024 license: MIT organization: BAAI mteb_overall: 64.23 mteb_retrieval: 54.29 mteb_sts: 83.11 mteb_clustering: 46.08 nvidia/NV-Embed-v1: link: https://huggingface.co/nvidia/NV-Embed-v1 revision: 77b11725df91ca45663471a0f2ec6c06e04cbadb desc: NV-Embed-v1 by Nvidia seq_len: 32768 size: 7851 dim: 4096 license: CC-BY-NC-4.0 organization: Nvidia mteb_overall: 69.32 mteb_retrieval: 59.36 mteb_sts: 82.84 mteb_clustering: 52.8 Alibaba-NLP/gte-Qwen2-7B-instruct: link: https://huggingface.co/Alibaba-NLP/gte-Qwen2-7B-instruct revision: e26182b2122f4435e8b3ebecbf363990f409b45b desc: gte-Qwen2-7B-instruct by Alibaba seq_len: 131072 size: 7613 dim: 3584 license: Apache 2.0 organization: Alibaba instruction_query_arxiv: Given a query, retrieve a relevant paper title and abstract from arXiv instruction_query_wikipedia: Given a query, retrieve a relevant title and passage from Wikipedia instruction_query_stackexchange: Given a query, retrieve a relevant question and answer from Stack Exchange instruction_clustering: Identify the topic/theme/category of the text instruction_sts: Retrieve semantically similar text mteb_overall: 70.24 mteb_retrieval: 60.25 mteb_sts: 83.04 mteb_clustering: 56.92 Salesforce/SFR-Embedding-2_R: link: https://huggingface.co/Salesforce/SFR-Embedding-2_R revision: 91762139d94ed4371a9fa31db5551272e0b83818 desc: SFR-Embedding-2_R by Salesforce seq_len: 32768 size: 7111 dim: 4096 license: CC-BY-NC-4.0 organization: Salesforce instruction_query_arxiv: Given a query, retrieve a relevant paper title and abstract from arXiv instruction_query_wikipedia: Given a query, retrieve a relevant title and passage from Wikipedia instruction_query_stackexchange: Given a query, retrieve a relevant question and answer from Stack Exchange instruction_clustering: Identify the topic/theme/category of the text instruction_sts: Retrieve semantically similar text mteb_overall: 70.31 mteb_retrieval: 60.18 mteb_sts: 81.26 mteb_clustering: 56.17 jinaai/jina-embeddings-v2-base-en: link: https://huggingface.co/jinaai/jina-embeddings-v2-base-en revision: 31b72fbf354fea65264ec54edf0b189d94b92d39 desc: jina-embeddings-v2-base-en by Jina AI seq_len: 8192 size: 137 dim: 768 license: Apache 2.0 organization: Jina AI mteb_overall: 60.38 mteb_retrieval: 47.87 mteb_sts: 80.70 mteb_clustering: 41.73 mixedbread-ai/mxbai-embed-large-v1: link: https://huggingface.co/mixedbread-ai/mxbai-embed-large-v1 revision: 990580e27d329c7408b3741ecff85876e128e203 desc: mxbai-embed-large-v1 by mixedbread.ai seq_len: 512 size: 335 dim: 1024 license: Apache 2.0 organization: mixedbread.ai mteb_overall: 64.68 mteb_retrieval: 54.39 mteb_sts: 85.00 mteb_clustering: 46.71 nomic-ai/nomic-embed-text-v1.5: link: https://huggingface.co/nomic-ai/nomic-embed-text-v1.5 revision: b0753ae76394dd36bcfb912a46018088bca48be0 desc: nomic-embed-text-v1.5 by nomic.ai seq_len: 8192 size: 137 dim: 768 license: Apache 2.0 organization: nomic.ai mteb_overall: 62.28 mteb_retrieval: 53.01 mteb_sts: 81.94 mteb_clustering: 43.93 McGill-NLP/LLM2Vec-Meta-Llama-3-8B-Instruct-mntp-supervised: link: https://huggingface.co/McGill-NLP/LLM2Vec-Meta-Llama-3-8B-Instruct-mntp-supervised revision: baa8ebf04a1c2500e61288e7dad65e8ae42601a7 desc: LLM2Vec by McGill seq_len: 8192 size: 7505 dim: 4096 license: MIT organization: McGill mteb_overall: 65.01 mteb_retrieval: 56.63 mteb_sts: 83.58 mteb_clustering: 46.45 voyage-multilingual-2: link: https://docs.voyageai.com/docs/embeddings revision: "1" desc: voyage-multilingual-2 by Voyage AI seq_len: 32000 dim: 1024 license: Proprietary organization: Voyage AI voyage-large-2-instruct: link: https://docs.voyageai.com/docs/embeddings revision: "1" desc: voyage-large-2-instruct by Voyage AI seq_len: 16000 dim: 1024 license: Proprietary organization: Voyage AI mteb_overall: 68.28 mteb_retrieval: 58.28 mteb_sts: 84.58 mteb_clustering: 53.35 text-embedding-004: link: https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/text-embeddings-api revision: "1" desc: text-embedding-004 by Google seq_len: 2048 dim: 768 license: Proprietary organization: Google mteb_overall: 66.31 mteb_retrieval: 55.7 mteb_sts: 85.07 mteb_clustering: 47.48 text-embedding-3-large: link: https://platform.openai.com/docs/guides/embeddings revision: "1" desc: text-embedding-3-large by OpenAI seq_len: 8191 dim: 3072 license: Proprietary organization: OpenAI mteb_overall: 64.59 mteb_retrieval: 55.44 mteb_sts: 81.73 mteb_clustering: 49.01 embed-english-v3.0: link: https://docs.cohere.com/docs/cohere-embed revision: "1" desc: embed-english-v3.0 by Cohere seq_len: 512 dim: 1024 license: Proprietary organization: Cohere mteb_overall: 64.47 mteb_retrieval: 55 mteb_sts: 82.62 mteb_clustering: 47.43 BM25: link: https://github.com/xhluca/bm25s desc: Fast lexical search via BM25 license: MIT mteb_retrieval: 42.4