# Embeddings benchmarks > Source: Benchize (https://benchize.com) — https://benchize.com/benchmarks/category/embeddings. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/benchmarks/category/embeddings. Explore Embeddings LLM benchmarks and AI model results. Compare source-reported scores with original metrics, evaluation settings and evidence on Benchize. Canonical URL: https://benchize.com/benchmarks/category/embeddings Last updated: 2026-10-21T18:52:20.672Z Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations. Compare text representations for search, retrieval, classification, and semantic similarity. Check the dataset, language, and retrieval setup before comparing embedding scores. Published Oct 21, 2026 ## [RTEB(Law, beta) · RTEB Legal](https://benchize.com/benchmarks/mteb%3ARTEB(Law%2C%20beta).md) Updated: 10/21/2026 Models tested: 17 Retrieval quality in the legal domain across case documents, statutes, legal summarization, and multilingual legal Q&A, with tasks representative of real-world production… Top models · MTEB Latest result per model · Version not reported - 1[Qwen3 Embedding](https://benchize.com/models/qwen3-embedding.md) - 2[Gemini Embedding 001](https://benchize.com/models/gemini-embedding-001.md) - 3[Text Embedding 3 Large](https://benchize.com/models/text-embedding-3-large.md) View details → ## [RTEB(deu, beta) · RTEB German](https://benchize.com/benchmarks/mteb%3ARTEB(deu%2C%20beta).md) Updated: 10/21/2026 Models tested: 17 Retrieval quality in German across legal, healthcare, and business domains, with tasks representative of real-world production retrieval demands. A German-language subset of RTEB.… Top models · MTEB Latest result per model · Version not reported - 1[Qwen3 Embedding](https://benchize.com/models/qwen3-embedding.md) - 2[Gemini Embedding 001](https://benchize.com/models/gemini-embedding-001.md) - 3[Text Embedding 3 Large](https://benchize.com/models/text-embedding-3-large.md) View details → ## [RTEB(fra, beta) · RTEB French](https://benchize.com/benchmarks/mteb%3ARTEB(fra%2C%20beta).md) Updated: 10/21/2026 Models tested: 17 Retrieval quality in French across legal and general knowledge domains, with tasks representative of real-world production retrieval demands. A French-language subset of RTEB.… Top models · MTEB Latest result per model · Version not reported - 1[Qwen3 Embedding](https://benchize.com/models/qwen3-embedding.md) - 2[Gemini Embedding 001](https://benchize.com/models/gemini-embedding-001.md) - 3[Text Embedding 3 Large](https://benchize.com/models/text-embedding-3-large.md) View details → ## [RTEB(Health, beta) · RTEB Healthcare](https://benchize.com/benchmarks/mteb%3ARTEB(Health%2C%20beta).md) Updated: 10/21/2026 Models tested: 14 Retrieval quality in the healthcare and medical domain across medical Q&A, healthcare information retrieval, and multilingual medical consultation, with tasks representative of… Top models · MTEB Latest result per model · Version not reported - 1[Qwen3 Embedding](https://benchize.com/models/qwen3-embedding.md) - 2[Gemini Embedding 001](https://benchize.com/models/gemini-embedding-001.md) - 3[Gemini Embedding 2](https://benchize.com/models/gemini-embedding-2.md) View details → ## [RTEB(fin, beta) · RTEB Finance](https://benchize.com/benchmarks/mteb%3ARTEB(fin%2C%20beta).md) Updated: 10/21/2026 Models tested: 13 Retrieval quality in the financial domain across finance benchmarks, Q&A, financial document retrieval, and corporate governance, with tasks representative of real-world… Top models · MTEB Latest result per model · Version not reported - 1[Gemini Embedding 2](https://benchize.com/models/gemini-embedding-2.md) - 2[Gemini Embedding 001](https://benchize.com/models/gemini-embedding-001.md) - 3[Qwen3 Embedding](https://benchize.com/models/qwen3-embedding.md) View details → ## [FollowIR · Instruction Following](https://benchize.com/benchmarks/mteb%3AFollowIR.md) Updated: 10/21/2026 Models tested: 15 Instruction-following retrieval quality, measuring how well models retrieve relevant documents when given detailed natural language instructions alongside queries. Top models · MTEB Latest result per model · Version not reported - 1[Qwen3 Embedding](https://benchize.com/models/qwen3-embedding.md) - 2[Gemini Embedding 001](https://benchize.com/models/gemini-embedding-001.md) - 3[all-MiniLM-L12-v2](https://benchize.com/models/all-minilm-l12-v2.md) View details → ## [BEIR](https://benchize.com/benchmarks/mteb%3ABEIR.md) Updated: 10/21/2026 Models tested: 14 Zero-shot retrieval quality across a heterogeneous set of IR tasks and domains, providing a common framework for comparing NLP-based retrieval models. Top models · MTEB Latest result per model · Version not reported - 1[Qwen3 Embedding](https://benchize.com/models/qwen3-embedding.md) - 2[Text Embedding 3 Large](https://benchize.com/models/text-embedding-3-large.md) - 3[BGE Large EN V1.5](https://benchize.com/models/bge-large-en-v1-5.md) View details → ## [LongEmbed · Long-context Retrieval](https://benchize.com/benchmarks/mteb%3ALongEmbed.md) Updated: 10/21/2026 Models tested: 13 Long-context retrieval quality across synthetic and real-world tasks featuring documents of varying length with dispersed target information. Top models · MTEB Latest result per model · Version not reported - 1[Bge m3](https://benchize.com/models/bge-m3.md) - 2[Text Embedding 3 Small](https://benchize.com/models/text-embedding-3-small.md) - 3[Text Embedding 3 Large](https://benchize.com/models/text-embedding-3-large.md) View details → ## [ChemTEB · Chemical](https://benchize.com/benchmarks/mteb%3AChemTEB.md) Updated: 10/21/2026 Models tested: 13 Chemical domain text embedding quality across bitext mining, classification, clustering, pair classification, and retrieval. Top models · MTEB Latest result per model · Version not reported - 1[Text Embedding 3 Large](https://benchize.com/models/text-embedding-3-large.md) - 2[Text Embedding 3 Small](https://benchize.com/models/text-embedding-3-small.md) - 3[Text Embedding Ada 002](https://benchize.com/models/text-embedding-ada-002.md) View details → ## [MTEB(Law, v1) · Legal](https://benchize.com/benchmarks/mteb%3AMTEB(Law%2C%20v1).md) Updated: 10/21/2026 Models tested: 12 Legal document retrieval across case documents, statutes, legal Q&A, and legal summarization in multiple languages. Top models · MTEB Latest result per model · Version not reported - 1[Text Embedding 3 Large](https://benchize.com/models/text-embedding-3-large.md) - 2[Text Embedding 3 Small](https://benchize.com/models/text-embedding-3-small.md) - 3[Multilingual-E5-Large](https://benchize.com/models/multilingual-e5-large.md) View details → ## [MTEB(deu, v1) · German](https://benchize.com/benchmarks/mteb%3AMTEB(deu%2C%20v1).md) Updated: 10/21/2026 Models tested: 10 German text embedding quality across classification, clustering, pair classification, reranking, retrieval, and semantic similarity. Top models · MTEB Latest result per model · Version not reported - 1[Multilingual-E5-Large](https://benchize.com/models/multilingual-e5-large.md) - 2[E5-Large-v2](https://benchize.com/models/e5-large-v2.md) - 3[GTE-Large](https://benchize.com/models/gte-large.md) View details → ## [MTEB(nld, v1) · Dutch](https://benchize.com/benchmarks/mteb%3AMTEB(nld%2C%20v1).md) Updated: 10/21/2026 Models tested: 10 Dutch text embedding quality across classification, clustering, pair classification, multilabel classification, reranking, retrieval, and semantic similarity. Top models · MTEB Latest result per model · Version not reported - 1[Qwen3 Embedding](https://benchize.com/models/qwen3-embedding.md) - 2[Bge m3](https://benchize.com/models/bge-m3.md) - 3[Multilingual-E5-Large](https://benchize.com/models/multilingual-e5-large.md) View details → ## [MTEB(Medical, v1) · Medical](https://benchize.com/benchmarks/mteb%3AMTEB(Medical%2C%20v1).md) Updated: 10/21/2026 Models tested: 8 Medical information retrieval across clinical, biomedical, and consumer health domains, spanning retrieval, reranking, and clustering tasks. Top models · MTEB Latest result per model · Version not reported - 1[Text Embedding 3 Large](https://benchize.com/models/text-embedding-3-large.md) - 2[Text Embedding 3 Small](https://benchize.com/models/text-embedding-3-small.md) - 3[GTE-Large](https://benchize.com/models/gte-large.md) View details → ## [MTEB(Indic, v1) · Indic](https://benchize.com/benchmarks/mteb%3AMTEB(Indic%2C%20v1).md) Updated: 10/21/2026 Models tested: 7 Text embedding quality across Indic languages spanning bitext mining, classification, clustering, pair classification, retrieval, reranking, and semantic similarity. Top models · MTEB Latest result per model · Version not reported - 1[E5-Large-v2](https://benchize.com/models/e5-large-v2.md) - 2[E5-Base-v2](https://benchize.com/models/e5-base-v2.md) - 3[BGE Base EN V1.5](https://benchize.com/models/bge-base-en-v1-5.md) View details → ## [MTEB(fra, v1) · French](https://benchize.com/benchmarks/mteb%3AMTEB(fra%2C%20v1).md) Updated: 10/21/2026 Models tested: 7 French text embedding quality across classification, clustering, pair classification, reranking, retrieval, and semantic similarity, using high-quality native French datasets. Top models · MTEB Latest result per model · Version not reported - 1[E5-Large-v2](https://benchize.com/models/e5-large-v2.md) - 2[BGE Large EN V1.5](https://benchize.com/models/bge-large-en-v1-5.md) - 3[GTE-Large](https://benchize.com/models/gte-large.md) View details → ## [MTEB(rus, v1.1) · Russian](https://benchize.com/benchmarks/mteb%3AMTEB(rus%2C%20v1.1).md) Updated: 10/21/2026 Models tested: 7 Russian text embedding quality across classification, clustering, reranking, pair classification, retrieval, and semantic similarity. In v1.1, MIRACLRetrieval and RiaNewsRetrieval… Top models · MTEB Latest result per model · Version not reported - 1[Qwen3 Embedding](https://benchize.com/models/qwen3-embedding.md) - 2[Bge m3](https://benchize.com/models/bge-m3.md) - 3[E5-Large-v2](https://benchize.com/models/e5-large-v2.md) View details → ## [MTEB(Europe, v1) · European](https://benchize.com/benchmarks/mteb%3AMTEB(Europe%2C%20v1).md) Updated: 10/21/2026 Models tested: 5 Text embedding quality across European languages spanning bitext mining, classification, clustering, pair classification, retrieval, reranking, and semantic similarity. Top models · MTEB Latest result per model · Version not reported - 1[E5-Large-v2](https://benchize.com/models/e5-large-v2.md) - 2[E5-Base-v2](https://benchize.com/models/e5-base-v2.md) - 3[BGE Large EN V1.5](https://benchize.com/models/bge-large-en-v1-5.md) View details → ## [MTEB(spa, v1) · Spanish](https://benchize.com/benchmarks/mteb%3AMTEB(spa%2C%20v1).md) Updated: 10/21/2026 Models tested: 5 Spanish text embedding quality across classification, clustering, pair classification, reranking, retrieval, and semantic similarity. For discussion on benchmark construction, see… Top models · MTEB Latest result per model · Version not reported - 1[Gemini Embedding 001](https://benchize.com/models/gemini-embedding-001.md) - 2[Text Embedding 3 Large](https://benchize.com/models/text-embedding-3-large.md) - 3[Text Embedding 3 Small](https://benchize.com/models/text-embedding-3-small.md) View details → ## [VN-MTEB (vie, v1) · Vietnamese](https://benchize.com/benchmarks/mteb%3AVN-MTEB%20(vie%2C%20v1).md) Updated: 10/21/2026 Models tested: 4 Vietnamese text embedding quality across retrieval, classification, pair classification, clustering, reranking, and semantic similarity. Top models · MTEB Latest result per model · Version not reported - 1[Bge m3](https://benchize.com/models/bge-m3.md) - 2[Multilingual-E5-Large](https://benchize.com/models/multilingual-e5-large.md) - 3[all-MiniLM-L12-v2](https://benchize.com/models/all-minilm-l12-v2.md) View details → ## [MTEB(Scandinavian, v1) · Scandinavian](https://benchize.com/benchmarks/mteb%3AMTEB(Scandinavian%2C%20v1).md) Updated: 10/21/2026 Models tested: 4 Scandinavian text embedding quality covering Danish, Swedish, Norwegian Bokmål, and Nynorsk and spanning classification, clustering, retrieval as well as bitext tasks across… Top models · MTEB Latest result per model · Version not reported - 1[Text Embedding 3 Large](https://benchize.com/models/text-embedding-3-large.md) - 2[Text Embedding 3 Small](https://benchize.com/models/text-embedding-3-small.md) - 3[Bge m3](https://benchize.com/models/bge-m3.md) View details → ## [MTEB(fas, v2) · Persian](https://benchize.com/benchmarks/mteb%3AMTEB(fas%2C%20v2).md) Updated: 10/21/2026 Models tested: 3 Persian text embedding quality across classification, clustering, pair classification, reranking, retrieval, semantic similarity, and summarization retrieval. In v2, large… Top models · MTEB Latest result per model · Version not reported - 1[Bge m3](https://benchize.com/models/bge-m3.md) - 2[Multilingual-E5-Large](https://benchize.com/models/multilingual-e5-large.md) - 3[Text Embedding 3 Small](https://benchize.com/models/text-embedding-3-small.md) View details → ## [BRIGHT · Reasoning Retrieval](https://benchize.com/benchmarks/mteb%3ABRIGHT.md) Updated: 10/21/2026 Models tested: 3 Reasoning-intensive retrieval quality across real-world queries spanning diverse domains including economics, psychology, mathematics, and coding, drawn from naturally occurring… Top models · MTEB Latest result per model · Version not reported - 1[Text Embedding 3 Large](https://benchize.com/models/text-embedding-3-large.md) - 2[All Mpnet Base V2](https://benchize.com/models/all-mpnet-base-v2.md) - 3[BGE Large EN V1.5](https://benchize.com/models/bge-large-en-v1-5.md) View details → ## [MTEB(tha, v1) · Thai](https://benchize.com/benchmarks/mteb%3AMTEB(tha%2C%20v1).md) Updated: 10/21/2026 Models tested: 3 Thai text embedding quality across classification, clustering, pair classification, reranking, and retrieval. Tasks are native Thai or high-quality human translations;… Top models · MTEB Latest result per model · Version not reported - 1[Bge m3](https://benchize.com/models/bge-m3.md) - 2[All Mpnet Base V2](https://benchize.com/models/all-mpnet-base-v2.md) - 3[all-MiniLM-L6-v2](https://benchize.com/models/all-minilm-l6-v2.md) View details → ## [MTEB(cmn, v1) · Chinese](https://benchize.com/benchmarks/mteb%3AMTEB(cmn%2C%20v1).md) Updated: 10/21/2026 Models tested: 2 Chinese text embedding quality across retrieval, reranking, pair classification, clustering, classification, and semantic similarity. Top models · MTEB Latest result per model · Version not reported - 1[Qwen3 Embedding](https://benchize.com/models/qwen3-embedding.md) - 2[Multilingual-E5-Large](https://benchize.com/models/multilingual-e5-large.md) View details → ## [BEIR-NL](https://benchize.com/benchmarks/mteb%3ABEIR-NL.md) Updated: 10/21/2026 Models tested: 2 Zero-shot retrieval quality in Dutch across the BEIR task suite, created through automated translation of the original English benchmark. Top models · MTEB Latest result per model · Version not reported - 1[Multilingual-E5-Large](https://benchize.com/models/multilingual-e5-large.md) - 2[Bge m3](https://benchize.com/models/bge-m3.md) View details → ## [MTEB(Code, v1) · Code](https://benchize.com/benchmarks/mteb%3AMTEB(Code%2C%20v1).md) Updated: 10/21/2026 Models tested: 2 Code retrieval quality across a wide range of popular programming languages, covering code search, text-to-SQL, and code feedback tasks. Top models · MTEB Latest result per model · Version not reported - 1[Qwen3 Embedding](https://benchize.com/models/qwen3-embedding.md) - 2[Gemini Embedding 001](https://benchize.com/models/gemini-embedding-001.md) View details → ## [CoIR · Code Information Retrieval](https://benchize.com/benchmarks/mteb%3ACoIR.md) Updated: 10/21/2026 Models tested: 2 Code information retrieval across diverse programming languages and coding tasks, including code search, question answering, and text-to-SQL retrieval. Top models · MTEB Latest result per model · Version not reported - 1[Qwen3 Embedding](https://benchize.com/models/qwen3-embedding.md) - 2[Gemini Embedding 001](https://benchize.com/models/gemini-embedding-001.md) View details → ## [MAEB(v1, audio-only) · MAEB Audio-Only](https://benchize.com/benchmarks/mteb%3AMAEB(v1%2C%20audio-only).md) Updated: 10/21/2026 Models tested: 1 Audio-only embedding quality across classification, clustering, pair classification, reranking, and retrieval tasks. Top models · MTEB Latest result per model · Version not reported - 1[Whisper Large v3](https://benchize.com/models/whisper-large-v3.md) View details → ## [RTEB(eng, beta) · RTEB English](https://benchize.com/benchmarks/mteb%3ARTEB(eng%2C%20beta).md) Updated: 10/21/2026 Models tested: 1 Retrieval quality in English across legal, finance, code, and healthcare domains, with tasks representative of real-world production retrieval demands. An English-only subset of… Top models · MTEB Latest result per model · Version not reported - 1[E5-Base-v2](https://benchize.com/models/e5-base-v2.md) View details → ## [RTEB(Code, beta) · RTEB Code](https://benchize.com/benchmarks/mteb%3ARTEB(Code%2C%20beta).md) Updated: 10/21/2026 Models tested: 1 Retrieval quality in the code domain across algorithmic problems, data science tasks, code evaluation, SQL retrieval, and multilingual code retrieval, with tasks representative of… Top models · MTEB Latest result per model · Version not reported - 1[E5-Base-v2](https://benchize.com/models/e5-base-v2.md) View details → ## [MTEB(por, v1) · Portuguese](https://benchize.com/benchmarks/mteb%3AMTEB(por%2C%20v1).md) Updated: 10/21/2026 Models tested: 1 Portuguese text embedding quality benchmark across semantic text similarity, classification, reranking and retrieval. Top models · MTEB Latest result per model · Version not reported - 1[Multilingual-E5-Large](https://benchize.com/models/multilingual-e5-large.md) View details → ## [CoREB(v1) · CoREB](https://benchize.com/benchmarks/mteb%3ACoREB(v1).md) Updated: 10/21/2026 Models tested: 1 Code embedding and reranking quality across code-to-text, text-to-code, and code-to-code retrieval tasks, using counterfactually rewritten problems in five programming languages… Top models · MTEB Latest result per model · Version not reported - 1[Qwen3 Embedding](https://benchize.com/models/qwen3-embedding.md) View details → ## [MTEB(kor, v2) · Korean](https://benchize.com/benchmarks/mteb%3AMTEB(kor%2C%20v2).md) Updated: 10/21/2026 Models tested: 1 Korean text embedding quality across classification, clustering, pair classification (NLI), reranking, retrieval, and semantic similarity. Expanded successor to MTEB(kor, v1):… Top models · MTEB Latest result per model · Version not reported - 1[Qwen3 Embedding](https://benchize.com/models/qwen3-embedding.md) View details → ## Methodology and provenance Benchize collects and structures public benchmark reports. Scores, costs, timings, ranks and uncertainty remain attributed to their original sources. Different versions, configurations and measurement units are separate results. Missing fields stay unavailable. --- Cite as: Embeddings benchmarks — Benchize, https://benchize.com/benchmarks/category/embeddings (retrieved 2026-10-21)