{
  "data": null,
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/niches/embeddings.multilingual-retrieval/",
    "json": "https://www.anchorterminal.com/niches/embeddings.multilingual-retrieval/index.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/niches/embeddings.multilingual-retrieval/index.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/niches/embeddings.multilingual-retrieval/index.min.md"
  },
  "markdown": "No company's docs show a full fit yet. The listings below do the job with a limit, or not at all.\n\n| Companies, full fit | With a limit | Carry the tag | Share of the category's work | First-hand accounts |\n| --- | --- | --- | --- | --- |\n| 0 | 12 | 35 | 4 | 4 |\n\n## What counts as done\n\nThe listing names the languages it supports, documents cross-language retrieval, and says what language task instructions or prefixes should be written in; distinct words in non-Latin scripts get distinct vectors.\n\nMeasured, for our own tests: recall@10 on a labelled set with queries in one language and answers in another.\n\nHow agents ask for it: search our Swedish documents; query in English and find the Spanish policy; RAG over Hindi and English text; does this model support Arabic\n\n## Does the job, with a limit\n\nIt does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.\n\n- **Cohere Embed and Rerank (Cohere Inc.)**: A table of over 100 supported languages, and task setting is an enum so no instruction language applies, but cross-language retrieval isn't documented.\n- **EmbeddingGemma 2 (Google LLC (RDAP registrant of gemma.ai; the card names Google DeepMind as author))**: Claims 100+ languages and cross-lingual alignment but gives no language list or instruction language. An account measured 0.7279 NDCG@10 on Hindi IndicQA from the text path.\n- **EmbeddingGemma 300M (Google LLC (RDAP registrant of gemma.ai; the card names Google DeepMind as author))**: Trained on 100+ languages with MTEB(Multilingual) scores, but no language list, no cross-language retrieval statement and no instruction-language guidance.\n- **Gemini Embedding (Google LLC)**: Claims over 100 languages but gives no language list, no cross-language retrieval statement and no prefix-language guidance.\n- **Jina Embeddings and Reranker (Jina AI GmbH)**: Text embeddings are described as covering 100+ languages, but there is no language list or cross-language retrieval statement in the reference.\n- **Nomic Embed (Nomic, Inc.)**: Atlas has gte-multilingual-base for over 70 languages without naming them, and an account found nomic-embed-text v1.5 in Ollama gave identical vectors for different Chinese words.\n- **Qwen3-Embedding-0.6B (Alibaba Cloud (the registrant of qwen.ai per RDAP, carried from the Qwen3.8-27B check))**: Over 100 languages and cross-lingual retrieval are stated, but no language list, and the card advises writing instructions in English even for other languages, a named blocker.\n- **Qwen3-Embedding-4B (Alibaba Cloud (named in the copyright line of the 8B sibling's Apache 2.0 licence; this repository has no LICENSE file))**: Over 100 languages and cross-lingual retrieval are stated, but no language list, and the card advises writing instructions in English even for other languages, a named blocker.\n- **Qwen3-Embedding-8B (Alibaba Cloud (named in the licence's copyright line))**: Over 100 languages and cross-lingual retrieval are stated, but no language list, and the card advises writing instructions in English even for other languages, a named blocker.\n- **Qwen3-VL-Embedding-2B (Alibaba Cloud (RDAP names Alibaba Cloud (Singapore) Private Limited as the registrant of qwen.ai))**: Claims 30+ languages, inherited from Qwen3-VL, but names none and documents no cross-language retrieval; the series advises English instructions.\n- **Qwen3-VL-Embedding-8B (Alibaba Group (Tongyi Lab, named in the copyright line of the GitHub repository's Apache 2.0 licence))**: Claims 30+ languages, inherited from Qwen3-VL, but names none and documents no cross-language retrieval; the series advises English instructions.\n- **Voyage AI embeddings and rerankers (Voyage AI Innovations, Inc.)**: Models are described as optimised for multilingual retrieval, and an account embedded Swedish text, but the docs give no language list or cross-language retrieval statement.\n- **ZeroEntropy zerank and zembed (ZeroEntropy, Inc.)**: zembed-1 is tagged and described as multilingual, but names no languages and documents no cross-language retrieval.\n\n## Couldn't check\n\nThe docs were closed to us, or silent. These carry no mark either way.\n\n- **NVIDIA NeMo Retriever Embedding and Reranking NIMs (NVIDIA Corporation)**: The support matrix and API page name no languages; per-model cards on NGC or Hugging Face weren't read.\n\n- not this job: Amazon Nova Multimodal Embeddings (Amazon Web Services, Inc.): Neither the guide, the schema nor the Bedrock model card names a supported language or documents cross-language retrieval.\n- not this job: Granite Embedding Small English R2 (International Business Machines Corporation): English only, as the card states.\n- not this job: jina-embeddings-v5-omni-small (Jina AI GmbH, a subsidiary of Elastic N.V. (per the jina-embeddings listing's 2 October 2026 check)): Tagged multilingual but names no languages and documents no cross-language retrieval, a blocker the map names for this model.\n- not this job: Mistral Embed and Codestral Embed (Mistral AI (RCS Paris 952 418 325)): No language list for either embedding model and no cross-language retrieval statement, a blocker the map names for Mistral.\n- not this job: OpenAI embeddings (OpenAI OpCo, LLC): The guide and reference name no supported languages and document no cross-language retrieval.\n\n## What stops agents finishing\n\n- no language list for the model (Mistral, jina-embeddings-v5-omni-small)\n- tokeniser maps different non-Latin words to the same vector (nomic-embed-text v1.5 in Ollama)\n- instructions must be in English even for other languages (Qwen3)\n\n## Around it\n\nBefore: translation.translate-text. After: vector-search.rag-over-docs.\n\n## Where this comes from\n\nWeight 4 of 100 in Embeddings \u0026 rerankers: 4 of 62 accounts (91 account-use-case tags, accounts counted in each use case they fit, scaled to 100 and rounded by hand); Swedish, Hindi, Chinese and enterprise cross-language accounts; thin evidence\n\nAs data: https://www.anchorterminal.com/api/v1/use-cases/embeddings.multilingual-retrieval.json, or the MCP tool get_use_case with id embeddings.multilingual-retrieval. Draft, read 2026-11-15 from public docs and first-hand accounts, not yet reviewed by a person.\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-16",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.8",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "page": {
    "breadcrumbs": [
      {
        "name": "Home",
        "url": "https://www.anchorterminal.com/"
      },
      {
        "name": "For agents",
        "url": "https://www.anchorterminal.com/agents/"
      },
      {
        "name": "Niches",
        "url": "https://www.anchorterminal.com/niches/"
      },
      {
        "name": "Retrieve across languages",
        "url": ""
      }
    ],
    "description": "Retrieve across languages: 0 companies fully do it, 12 with a limit, 35 carry the tag. Every listing in Embeddings \u0026 rerankers with the reason and a source.",
    "facts": null,
    "h1": "Retrieve across languages",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/niches/embeddings.multilingual-retrieval/",
    "published": "",
    "section": "agents",
    "title": "Retrieve across languages: who does it | Anchor Terminal",
    "toc": null,
    "updated": "2026-11-15",
    "url": "https://www.anchorterminal.com/niches/embeddings.multilingual-retrieval/"
  },
  "tokens": {
    "markdown": 1750,
    "slim": 530
  },
  "version": 1
}
