{
  "listings": [
    {
      "slug": "embeddinggemma-2",
      "name": "EmbeddingGemma 2",
      "company": "Google LLC (RDAP registrant of gemma.ai; the card names Google DeepMind as author)",
      "grade": "B",
      "fit": "yes",
      "why": "A CodeRetrieval prompt for natural-language queries against code, an MTEB(Code, v1) score of 78.68 on the card, and it runs locally. NaN only in float16, which the card rules out.",
      "source": "https://huggingface.co/google/embeddinggemma-2/raw/main/README.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/embeddinggemma-2"
    },
    {
      "slug": "embeddinggemma-300m",
      "name": "EmbeddingGemma 300M",
      "company": "Google LLC (RDAP registrant of gemma.ai; the card names Google DeepMind as author)",
      "grade": "D",
      "fit": "yes",
      "why": "A Code Retrieval prompt for natural-language queries against code blocks, MTEB(Code, v1) 68.76 published on the card, and a local route. Code recall against grep unmeasured.",
      "source": "https://gemma.ai/models/embeddinggemma/model-card-v1.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/embeddinggemma-300m"
    },
    {
      "slug": "granite-embedding-small-english-r2",
      "name": "Granite Embedding Small English R2",
      "company": "International Business Machines Corporation",
      "grade": "E",
      "fit": "yes",
      "why": "Code retrieval results are published (CoIR 53.8 over 10 tasks), it runs locally, and no report of code-token failures was found in the publisher repository's 7 issues. Recall against grep unmeasured.",
      "source": "https://huggingface.co/ibm-granite/granite-embedding-small-english-r2/raw/main/README.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/granite-embedding-small-english-r2"
    },
    {
      "slug": "gemini-embedding",
      "name": "Gemini Embedding",
      "company": "Google LLC",
      "grade": "B",
      "fit": "caveat",
      "why": "A task: code retrieval prefix embeds natural-language queries against code, and retention is stated, but free-tier inputs are used to improve Google products and may be read by human reviewers; only the paid tier excludes it.",
      "source": "https://ai.google.dev/gemini-api/docs/embeddings.md.txt",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/gemini-embedding"
    },
    {
      "slug": "jina-embeddings",
      "name": "Jina Embeddings and Reranker",
      "company": "Jina AI GmbH",
      "grade": "B",
      "fit": "caveat",
      "why": "Code embedding models take nl2code.query and nl2code.passage tasks, but retention of uploaded code wasn't stated on any page read here.",
      "source": "https://docs.jina.ai/api.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/jina-embeddings"
    },
    {
      "slug": "mistral-embeddings",
      "name": "Mistral Embed and Codestral Embed",
      "company": "Mistral AI (RCS Paris 952 418 325)",
      "grade": "B",
      "fit": "caveat",
      "why": "codestral-embed is a code model for retrieval over code, but it is hosted and retention of uploaded code wasn't confirmed on the pages read; the free tier may train on inputs per the last assessment.",
      "source": "https://docs.mistral.ai/studio/knowledge-rag/embeddings/code_embeddings.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/mistral-embeddings"
    },
    {
      "slug": "nomic-embed",
      "name": "Nomic Embed",
      "company": "Nomic, Inc.",
      "grade": "E",
      "fit": "caveat",
      "why": "No code model or code results on the Atlas pages, though an account found Ollama with Nomic fast enough to index a codebase for the Roo agent.",
      "source": "https://docs.nomic.ai/atlas/embeddings-and-retrieval/text-embedding",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/nomic-embed"
    },
    {
      "slug": "openai-embeddings",
      "name": "OpenAI embeddings",
      "company": "OpenAI OpCo, LLC",
      "grade": "BB",
      "fit": "caveat",
      "why": "No code model or code retrieval results; the guide shows code search over Python functions with text-embedding-3-small, and retention for uploaded code wasn't on the pages read.",
      "source": "https://developers.openai.com/api/docs/guides/embeddings.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/openai-embeddings"
    },
    {
      "slug": "qwen3-embedding-0-6b",
      "name": "Qwen3-Embedding-0.6B",
      "company": "Alibaba Cloud (the registrant of qwen.ai per RDAP, carried from the Qwen3.8-27B check)",
      "grade": "B",
      "fit": "caveat",
      "why": "The card claims code retrieval and support for programming languages, but publishes no code retrieval results; it runs locally, so no code leaves the machine.",
      "source": "https://huggingface.co/Qwen/Qwen3-Embedding-0.6B/raw/main/README.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/qwen3-embedding-0-6b"
    },
    {
      "slug": "qwen3-embedding-4b",
      "name": "Qwen3-Embedding-4B",
      "company": "Alibaba Cloud (named in the copyright line of the 8B sibling's Apache 2.0 licence; this repository has no LICENSE file)",
      "grade": "BB",
      "fit": "caveat",
      "why": "The card claims code retrieval and support for programming languages, but publishes no code retrieval results; it runs locally, so no code leaves the machine.",
      "source": "https://huggingface.co/Qwen/Qwen3-Embedding-4B/raw/main/README.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/qwen3-embedding-4b"
    },
    {
      "slug": "qwen3-embedding-8b",
      "name": "Qwen3-Embedding-8B",
      "company": "Alibaba Cloud (named in the licence's copyright line)",
      "grade": "BB",
      "fit": "caveat",
      "why": "Code retrieval is claimed without published code results, and an account found any text containing \"import\" returned an all-NaN vector in float16, a named blocker.",
      "source": "https://huggingface.co/Qwen/Qwen3-Embedding-8B/raw/main/README.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/qwen3-embedding-8b"
    },
    {
      "slug": "voyage-ai",
      "name": "Voyage AI embeddings and rerankers",
      "company": "Voyage AI Innovations, Inc.",
      "grade": "B",
      "fit": "caveat",
      "why": "voyage-code-4 is a code retrieval model and retention is stated, but inputs train models by default with a one-way opt-out, and an account benchmarking coding agents went back to ripgrep.",
      "source": "https://docs.voyageai.com/docs/embeddings.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/voyage-ai"
    },
    {
      "slug": "zeroentropy",
      "name": "ZeroEntropy zerank and zembed",
      "company": "ZeroEntropy, Inc.",
      "grade": "F",
      "fit": "caveat",
      "why": "The zembed-1 card publishes a code retrieval score (0.6452) and runs locally, but needs trust_remote_code.",
      "source": "https://huggingface.co/zeroentropy/zembed-1-embedding/raw/main/README.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/zeroentropy"
    },
    {
      "slug": "amazon-nova-embeddings",
      "name": "Amazon Nova Multimodal Embeddings",
      "company": "Amazon Web Services, Inc.",
      "grade": "BB",
      "fit": "no",
      "why": "No code model or code retrieval results in the guide, schema or model card, and it doesn't run locally.",
      "source": "https://docs.aws.amazon.com/nova/latest/userguide/nova-embeddings.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/amazon-nova-embeddings"
    },
    {
      "slug": "cohere-embed",
      "name": "Cohere Embed and Rerank",
      "company": "Cohere Inc.",
      "grade": "BB",
      "fit": "no",
      "why": "No code model and no code retrieval results on the models page, and no local route.",
      "source": "https://docs.cohere.com/docs/cohere-embed.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/cohere-embed"
    },
    {
      "slug": "jina-embeddings-v5-omni-small",
      "name": "jina-embeddings-v5-omni-small",
      "company": "Jina AI GmbH, a subsidiary of Elastic N.V. (per the jina-embeddings listing's 2 October 2026 check)",
      "grade": "D",
      "fit": "no",
      "why": "No code task, code model id or code retrieval results on the card.",
      "source": "https://huggingface.co/jinaai/jina-embeddings-v5-omni-small/raw/main/README.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/jina-embeddings-v5-omni-small"
    },
    {
      "slug": "nvidia-nemo-retriever",
      "name": "NVIDIA NeMo Retriever Embedding and Reranking NIMs",
      "company": "NVIDIA Corporation",
      "grade": "B",
      "fit": "no",
      "why": "None of the eight models in the support matrix is a code model, and no code retrieval results were found on the pages read.",
      "source": "https://docs.nvidia.com/nim/nemo-retriever/embedding/latest/support-matrix.html",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/nvidia-nemo-retriever"
    },
    {
      "slug": "qwen3-vl-embedding-2b",
      "name": "Qwen3-VL-Embedding-2B",
      "company": "Alibaba Cloud (RDAP names Alibaba Cloud (Singapore) Private Limited as the registrant of qwen.ai)",
      "grade": "C",
      "fit": "no",
      "why": "No code retrieval claim, code model id or code results on the card.",
      "source": "https://huggingface.co/Qwen/Qwen3-VL-Embedding-2B/raw/main/README.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/qwen3-vl-embedding-2b"
    },
    {
      "slug": "qwen3-vl-embedding-8b",
      "name": "Qwen3-VL-Embedding-8B",
      "company": "Alibaba Group (Tongyi Lab, named in the copyright line of the GitHub repository's Apache 2.0 licence)",
      "grade": "B",
      "fit": "no",
      "why": "No code retrieval claim, code model id or code results on the card.",
      "source": "https://huggingface.co/Qwen/Qwen3-VL-Embedding-8B/raw/main/README.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/qwen3-vl-embedding-8b"
    }
  ],
  "marks": "yes: the docs show it does the job as the success test says. caveat: it does the job with a limit an agent should know. no: it doesn't do this job. unchecked: we couldn't read it.",
  "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"
  },
  "useCase": {
    "accounts": 5,
    "after": [
      "vector-search.agent-query-tool"
    ],
    "area": "models",
    "asks": [
      "semantic search over this repo",
      "find where we handle refunds",
      "index the monorepo for the agent",
      "which function does this"
    ],
    "before": [
      "code.read-repo"
    ],
    "blockers": [
      "float16 NaN on common code tokens such as \"import\" (Qwen3-Embedding-8B)",
      "indexing too slow for a working repo",
      "the agent does as well with grep, so the index is not worth its cost"
    ],
    "capabilities": [
      "embed.code",
      "embed.text"
    ],
    "category": "embeddings",
    "categoryName": "Embeddings \u0026 rerankers",
    "checked": "2026-11-15",
    "companies": {
      "fit": 2,
      "fitWithLimit": 10,
      "tagged": 35
    },
    "competition": "few",
    "fits": [
      "embeddinggemma-2",
      "embeddinggemma-300m",
      "granite-embedding-small-english-r2"
    ],
    "fitsWithLimit": [
      "gemini-embedding",
      "jina-embeddings",
      "mistral-embeddings",
      "nomic-embed",
      "openai-embeddings",
      "qwen3-embedding-0-6b",
      "qwen3-embedding-4b",
      "qwen3-embedding-8b",
      "voyage-ai",
      "zeroentropy"
    ],
    "id": "embeddings.code-search",
    "listings": {
      "caveat": 10,
      "no": 6,
      "notRead": 0,
      "tagged": 37,
      "unchecked": 0,
      "yes": 3
    },
    "name": "Index a codebase for a coding agent",
    "status": "draft",
    "success": "A code-capable model (a code model id, or code retrieval results published) embeds code and natural-language queries into one space, handles code tokens without errors or NaN, and either runs locally or states retention for uploaded code. Measured: recall@10 on a labelled code query set compared with a grep baseline, and time to re-embed one changed file.",
    "url": "https://www.anchorterminal.com/api/v1/use-cases/embeddings.code-search.json",
    "weight": 5,
    "weightBasis": "5 of 62 accounts (91 account-use-case tags, accounts counted in each use case they fit, scaled to 100 and rounded by hand); Roo, ChunkHound and benchmark accounts; two accounts say grep or BM25 beat embeddings for code"
  }
}
