{
 "body": "\nPart of the [MTEB](mteb.md) family.\n\n## What it measures\n\nmteb_pair_classification takes pairs of sentences labelled as equivalent or not (paraphrases,\nduplicate questions) and uses the model's cosine similarity between each pair's embeddings as\na ranking score, evaluated by average precision rather than a fixed similarity threshold. It\ncovers 3 datasets in the original MTEB task set, primarily English, including duplicate\nquestion and tweet-paraphrase collections; dot-product and distance variants are also\ncomputed, but cosine-based average precision is the headline figure.\n\n## Reading the numbers\n\nA strong pair-classification score suggests a model's embedding space cleanly separates\nnear-duplicate meaning from superficial lexical overlap, which is useful for deduplication,\nplagiarism and duplicate-question detection pipelines. With only 3 datasets behind it, this is\na narrower signal than mteb_retrieval or mteb_classification, and a good average precision does\nnot by itself tell you what similarity threshold to pick for your own system \u2014 that still has\nto be calibrated against your own data.\n",
 "build": {
  "built_at": "2026-09-09T16:56:50+00:00",
  "commit": "0a599558854c0e238c03a0f0d725239cb28f9d11",
  "eligibility_as_of": "2026-09-09"
 },
 "disposition": {
  "canonical_id": "mteb_pair_classification",
  "reasons": [],
  "status": "unassessed",
  "verified_results": []
 },
 "models_covered": [
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "e5 mistral 7B instruct",
   "model_id": "intfloat/e5-mistral-7b-instruct",
   "provider": "intfloat",
   "provider_display": "intfloat",
   "score": 87.0,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "multilingual e5 large instruct",
   "model_id": "intfloat/multilingual-e5-large-instruct",
   "provider": "intfloat",
   "provider_display": "intfloat",
   "score": 86.2,
   "source": "mteb-leaderboard"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "SFR Embedding 2 R",
   "model_id": "salesforce/sfr-embedding-2-r",
   "provider": "salesforce",
   "provider_display": "Salesforce",
   "score": 86.0,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Voyage 3",
   "model_id": "voyage/voyage-3",
   "provider": "voyage",
   "provider_display": "Voyage AI",
   "score": 86.0,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Qwen3 Embedding 8B",
   "model_id": "qwen/qwen3-embedding-8b",
   "provider": "qwen",
   "provider_display": "Alibaba / Qwen Team",
   "score": 85.5,
   "source": "mteb-leaderboard"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Qwen3 VL Embedding 8B",
   "model_id": "qwen/qwen3-vl-embedding-8b",
   "provider": "qwen",
   "provider_display": "Alibaba / Qwen Team",
   "score": 85.5,
   "source": "mteb-leaderboard"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "snowflake arctic embed l v2.0",
   "model_id": "snowflake/snowflake-arctic-embed-l-v2-0",
   "provider": "snowflake",
   "provider_display": "Snowflake",
   "score": 85.5,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "text-embedding-3-large",
   "model_id": "openai/text-embedding-3-large",
   "provider": "openai",
   "provider_display": "OpenAI",
   "score": 85.5,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Gemini Embedding 001",
   "model_id": "google/gemini-embedding-001",
   "provider": "google",
   "provider_display": "Google DeepMind",
   "score": 85.1,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "bge large en v1.5",
   "model_id": "baai/bge-large-en-v1-5",
   "provider": "baai",
   "provider_display": "BAAI",
   "score": 85.0,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "bge multilingual gemma2",
   "model_id": "baai/bge-multilingual-gemma2",
   "provider": "baai",
   "provider_display": "BAAI",
   "score": 85.0,
   "source": "mteb-leaderboard"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "e5 large v2",
   "model_id": "intfloat/e5-large-v2",
   "provider": "intfloat",
   "provider_display": "intfloat",
   "score": 85.0,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Qwen3 Embedding 4B",
   "model_id": "qwen/qwen3-embedding-4b",
   "provider": "qwen",
   "provider_display": "Alibaba / Qwen Team",
   "score": 85.0,
   "source": "mteb-leaderboard"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "multilingual e5 large",
   "model_id": "intfloat/multilingual-e5-large",
   "provider": "intfloat",
   "provider_display": "intfloat",
   "score": 84.8,
   "source": "mteb-leaderboard"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "bge m3",
   "model_id": "baai/bge-m3",
   "provider": "baai",
   "provider_display": "BAAI",
   "score": 84.5,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "e5 large",
   "model_id": "intfloat/e5-large",
   "provider": "intfloat",
   "provider_display": "intfloat",
   "score": 84.5,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "e5 large unsupervised",
   "model_id": "intfloat/e5-large-unsupervised",
   "provider": "intfloat",
   "provider_display": "intfloat",
   "score": 84.5,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "granite embedding english r2",
   "model_id": "ibm/granite-embedding-english-r2",
   "provider": "ibm",
   "provider_display": "IBM",
   "score": 84.5,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "granite embedding small english r2",
   "model_id": "ibm/granite-embedding-small-english-r2",
   "provider": "ibm",
   "provider_display": "IBM",
   "score": 84.5,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "jina embeddings v4",
   "model_id": "jina/jina-embeddings-v4",
   "provider": "jina",
   "provider_display": "Jina AI",
   "score": 84.5,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "jina embeddings v4 vllm retrieval",
   "model_id": "jina/jina-embeddings-v4-vllm-retrieval",
   "provider": "jina",
   "provider_display": "Jina AI",
   "score": 84.5,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "jina embeddings v5 text nano",
   "model_id": "jina/jina-embeddings-v5-text-nano",
   "provider": "jina",
   "provider_display": "Jina AI",
   "score": 84.5,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "jina embeddings v5 text small",
   "model_id": "jina/jina-embeddings-v5-text-small",
   "provider": "jina",
   "provider_display": "Jina AI",
   "score": 84.5,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "jina embeddings v5 text small retrieval",
   "model_id": "jina/jina-embeddings-v5-text-small-retrieval",
   "provider": "jina",
   "provider_display": "Jina AI",
   "score": 84.5,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "snowflake arctic embed l",
   "model_id": "snowflake/snowflake-arctic-embed-l",
   "provider": "snowflake",
   "provider_display": "Snowflake",
   "score": 84.5,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "NV Embed v2",
   "model_id": "nvidia/nv-embed-v2",
   "provider": "nvidia",
   "provider_display": "NVIDIA",
   "score": 84.1,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "bge large en",
   "model_id": "baai/bge-large-en",
   "provider": "baai",
   "provider_display": "BAAI",
   "score": 84.0,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "colnomic embed multimodal 7B",
   "model_id": "nomic/colnomic-embed-multimodal-7b",
   "provider": "nomic",
   "provider_display": "Nomic AI",
   "score": 84.0,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "jina clip v2",
   "model_id": "jina/jina-clip-v2",
   "provider": "jina",
   "provider_display": "Jina AI",
   "score": 84.0,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "jina code embeddings 1.5B",
   "model_id": "jina/jina-code-embeddings-1-5b",
   "provider": "jina",
   "provider_display": "Jina AI",
   "score": 84.0,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "jina embeddings v3",
   "model_id": "jina/jina-embeddings-v3",
   "provider": "jina",
   "provider_display": "Jina AI",
   "score": 84.0,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "nomic embed multimodal 7B",
   "model_id": "nomic/nomic-embed-multimodal-7b",
   "provider": "nomic",
   "provider_display": "Nomic AI",
   "score": 84.0,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "nomic embed text v2 moe",
   "model_id": "nomic/nomic-embed-text-v2-moe",
   "provider": "nomic",
   "provider_display": "Nomic AI",
   "score": 84.0,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "nomic embed text v2 moe GGUF",
   "model_id": "nomic/nomic-embed-text-v2-moe-gguf",
   "provider": "nomic",
   "provider_display": "Nomic AI",
   "score": 84.0,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "snowflake arctic embed m v2.0",
   "model_id": "snowflake/snowflake-arctic-embed-m-v2-0",
   "provider": "snowflake",
   "provider_display": "Snowflake",
   "score": 84.0,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "e5 base v2",
   "model_id": "intfloat/e5-base-v2",
   "provider": "intfloat",
   "provider_display": "intfloat",
   "score": 83.5,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Voyage Code 3",
   "model_id": "voyage/voyage-code-3",
   "provider": "voyage",
   "provider_display": "Voyage AI",
   "score": 83.5,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Voyage Multilingual 2",
   "model_id": "voyage/voyage-multilingual-2",
   "provider": "voyage",
   "provider_display": "Voyage AI",
   "score": 83.5,
   "source": "mteb-leaderboard"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "bge base en v1.5",
   "model_id": "baai/bge-base-en-v1-5",
   "provider": "baai",
   "provider_display": "BAAI",
   "score": 83.2,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "e5 base",
   "model_id": "intfloat/e5-base",
   "provider": "intfloat",
   "provider_display": "intfloat",
   "score": 83.0,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "granite embedding 278M multilingual",
   "model_id": "ibm/granite-embedding-278m-multilingual",
   "provider": "ibm",
   "provider_display": "IBM",
   "score": 83.0,
   "source": "mteb-leaderboard"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "modernbert embed base",
   "model_id": "nomic/modernbert-embed-base",
   "provider": "nomic",
   "provider_display": "Nomic AI",
   "score": 83.0,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "multilingual e5 base",
   "model_id": "intfloat/multilingual-e5-base",
   "provider": "intfloat",
   "provider_display": "intfloat",
   "score": 83.0,
   "source": "mteb-leaderboard"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "nomic embed text v1.5",
   "model_id": "nomic/nomic-embed-text-v1-5",
   "provider": "nomic",
   "provider_display": "Nomic AI",
   "score": 83.0,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "nomic embed text v1.5 GGUF",
   "model_id": "nomic/nomic-embed-text-v1-5-gguf",
   "provider": "nomic",
   "provider_display": "Nomic AI",
   "score": 83.0,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "snowflake arctic embed m",
   "model_id": "snowflake/snowflake-arctic-embed-m",
   "provider": "snowflake",
   "provider_display": "Snowflake",
   "score": 83.0,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "snowflake arctic embed m v1.5",
   "model_id": "snowflake/snowflake-arctic-embed-m-v1-5",
   "provider": "snowflake",
   "provider_display": "Snowflake",
   "score": 83.0,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Voyage 3 Lite",
   "model_id": "voyage/voyage-3-lite",
   "provider": "voyage",
   "provider_display": "Voyage AI",
   "score": 83.0,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Voyage Finance 2",
   "model_id": "voyage/voyage-finance-2",
   "provider": "voyage",
   "provider_display": "Voyage AI",
   "score": 83.0,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "snowflake arctic embed m long",
   "model_id": "snowflake/snowflake-arctic-embed-m-long",
   "provider": "snowflake",
   "provider_display": "Snowflake",
   "score": 82.8,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Voyage Law 2",
   "model_id": "voyage/voyage-law-2",
   "provider": "voyage",
   "provider_display": "Voyage AI",
   "score": 82.8,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "bge base en",
   "model_id": "baai/bge-base-en",
   "provider": "baai",
   "provider_display": "BAAI",
   "score": 82.5,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "nomic embed text v1",
   "model_id": "nomic/nomic-embed-text-v1",
   "provider": "nomic",
   "provider_display": "Nomic AI",
   "score": 82.5,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "SFR Embedding Code 400M R",
   "model_id": "salesforce/sfr-embedding-code-400m-r",
   "provider": "salesforce",
   "provider_display": "Salesforce",
   "score": 82.5,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "bge code v1",
   "model_id": "baai/bge-code-v1",
   "provider": "baai",
   "provider_display": "BAAI",
   "score": 82.0,
   "source": "mteb-leaderboard"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "e5 small v2",
   "model_id": "intfloat/e5-small-v2",
   "provider": "intfloat",
   "provider_display": "intfloat",
   "score": 82.0,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Mistral Embed",
   "model_id": "mistral/mistral-embed",
   "provider": "mistral",
   "provider_display": "Mistral AI",
   "score": 82.0,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Qwen3 Embedding 0.6B",
   "model_id": "qwen/qwen3-embedding-0-6b",
   "provider": "qwen",
   "provider_display": "Alibaba / Qwen Team",
   "score": 82.0,
   "source": "mteb-leaderboard"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Qwen3 VL Embedding 2B",
   "model_id": "qwen/qwen3-vl-embedding-2b",
   "provider": "qwen",
   "provider_display": "Alibaba / Qwen Team",
   "score": 82.0,
   "source": "mteb-leaderboard"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "text-embedding-3-small",
   "model_id": "openai/text-embedding-3-small",
   "provider": "openai",
   "provider_display": "OpenAI",
   "score": 82.0,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "all mpnet base v2",
   "model_id": "sentence-transformers/all-mpnet-base-v2",
   "provider": "sentence-transformers",
   "provider_display": "Sentence Transformers",
   "score": 81.5,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "granite embedding 125M english",
   "model_id": "ibm/granite-embedding-125m-english",
   "provider": "ibm",
   "provider_display": "IBM",
   "score": 81.5,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "multilingual e5 small",
   "model_id": "intfloat/multilingual-e5-small",
   "provider": "intfloat",
   "provider_display": "intfloat",
   "score": 81.5,
   "source": "mteb-leaderboard"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "snowflake arctic embed s",
   "model_id": "snowflake/snowflake-arctic-embed-s",
   "provider": "snowflake",
   "provider_display": "Snowflake",
   "score": 81.5,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "all MiniLM L12 v2",
   "model_id": "sentence-transformers/all-minilm-l12-v2",
   "provider": "sentence-transformers",
   "provider_display": "Sentence Transformers",
   "score": 81.0,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "bge small en v1.5",
   "model_id": "baai/bge-small-en-v1-5",
   "provider": "baai",
   "provider_display": "BAAI",
   "score": 81.0,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "CodeRankEmbed",
   "model_id": "nomic/coderankembed",
   "provider": "nomic",
   "provider_display": "Nomic AI",
   "score": 81.0,
   "source": "mteb-leaderboard"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "e5 small",
   "model_id": "intfloat/e5-small",
   "provider": "intfloat",
   "provider_display": "intfloat",
   "score": 81.0,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "nomic embed code",
   "model_id": "nomic/nomic-embed-code",
   "provider": "nomic",
   "provider_display": "Nomic AI",
   "score": 81.0,
   "source": "mteb-leaderboard"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "all MiniLM L6 v2",
   "model_id": "sentence-transformers/all-minilm-l6-v2",
   "provider": "sentence-transformers",
   "provider_display": "Sentence Transformers",
   "score": 80.5,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "bge small en",
   "model_id": "baai/bge-small-en",
   "provider": "baai",
   "provider_display": "BAAI",
   "score": 80.5,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "granite embedding 107M multilingual",
   "model_id": "ibm/granite-embedding-107m-multilingual",
   "provider": "ibm",
   "provider_display": "IBM",
   "score": 80.5,
   "source": "mteb-leaderboard"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "text-embedding-ada-002",
   "model_id": "openai/text-embedding-ada-002",
   "provider": "openai",
   "provider_display": "OpenAI",
   "score": 80.2,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "multi qa mpnet base dot v1",
   "model_id": "sentence-transformers/multi-qa-mpnet-base-dot-v1",
   "provider": "sentence-transformers",
   "provider_display": "Sentence Transformers",
   "score": 80.0,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "paraphrase mpnet base v2",
   "model_id": "sentence-transformers/paraphrase-mpnet-base-v2",
   "provider": "sentence-transformers",
   "provider_display": "Sentence Transformers",
   "score": 80.0,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "multi qa mpnet base cos v1",
   "model_id": "sentence-transformers/multi-qa-mpnet-base-cos-v1",
   "provider": "sentence-transformers",
   "provider_display": "Sentence Transformers",
   "score": 79.8,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "all roberta large v1",
   "model_id": "sentence-transformers/all-roberta-large-v1",
   "provider": "sentence-transformers",
   "provider_display": "Sentence Transformers",
   "score": 79.5,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "snowflake arctic embed xs",
   "model_id": "snowflake/snowflake-arctic-embed-xs",
   "provider": "snowflake",
   "provider_display": "Snowflake",
   "score": 79.5,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "all distilroberta v1",
   "model_id": "sentence-transformers/all-distilroberta-v1",
   "provider": "sentence-transformers",
   "provider_display": "Sentence Transformers",
   "score": 79.0,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "paraphrase multilingual mpnet base v2",
   "model_id": "sentence-transformers/paraphrase-multilingual-mpnet-base-v2",
   "provider": "sentence-transformers",
   "provider_display": "Sentence Transformers",
   "score": 79.0,
   "source": "mteb-leaderboard"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "granite embedding 30M english",
   "model_id": "ibm/granite-embedding-30m-english",
   "provider": "ibm",
   "provider_display": "IBM",
   "score": 78.5,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "granite embedding 30M sparse",
   "model_id": "ibm/granite-embedding-30m-sparse",
   "provider": "ibm",
   "provider_display": "IBM",
   "score": 78.5,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "msmarco bert base dot v5",
   "model_id": "sentence-transformers/msmarco-bert-base-dot-v5",
   "provider": "sentence-transformers",
   "provider_display": "Sentence Transformers",
   "score": 78.5,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "multi qa MiniLM L6 cos v1",
   "model_id": "sentence-transformers/multi-qa-minilm-l6-cos-v1",
   "provider": "sentence-transformers",
   "provider_display": "Sentence Transformers",
   "score": 78.5,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "paraphrase MiniLM L12 v2",
   "model_id": "sentence-transformers/paraphrase-minilm-l12-v2",
   "provider": "sentence-transformers",
   "provider_display": "Sentence Transformers",
   "score": 78.0,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "paraphrase multilingual MiniLM L12 v2",
   "model_id": "sentence-transformers/paraphrase-multilingual-minilm-l12-v2",
   "provider": "sentence-transformers",
   "provider_display": "Sentence Transformers",
   "score": 78.0,
   "source": "mteb-leaderboard"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "msmarco MiniLM L12 cos v5",
   "model_id": "sentence-transformers/msmarco-minilm-l12-cos-v5",
   "provider": "sentence-transformers",
   "provider_display": "Sentence Transformers",
   "score": 77.5,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "paraphrase MiniLM L6 v2",
   "model_id": "sentence-transformers/paraphrase-minilm-l6-v2",
   "provider": "sentence-transformers",
   "provider_display": "Sentence Transformers",
   "score": 77.5,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "msmarco MiniLM L6 v3",
   "model_id": "sentence-transformers/msmarco-minilm-l6-v3",
   "provider": "sentence-transformers",
   "provider_display": "Sentence Transformers",
   "score": 77.0,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "LaBSE",
   "model_id": "sentence-transformers/labse",
   "provider": "sentence-transformers",
   "provider_display": "Sentence Transformers",
   "score": 76.0,
   "source": "mteb-leaderboard"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "paraphrase MiniLM L3 v2",
   "model_id": "sentence-transformers/paraphrase-minilm-l3-v2",
   "provider": "sentence-transformers",
   "provider_display": "Sentence Transformers",
   "score": 75.5,
   "source": "mteb-leaderboard, miracl"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "distiluse base multilingual cased v2",
   "model_id": "sentence-transformers/distiluse-base-multilingual-cased-v2",
   "provider": "sentence-transformers",
   "provider_display": "Sentence Transformers",
   "score": 75.0,
   "source": "mteb-leaderboard"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "distiluse base multilingual cased v1",
   "model_id": "sentence-transformers/distiluse-base-multilingual-cased-v1",
   "provider": "sentence-transformers",
   "provider_display": "Sentence Transformers",
   "score": 73.5,
   "source": "mteb-leaderboard"
  }
 ],
 "page": {
  "aliases": [],
  "category": "embedding",
  "contamination": {
   "note": "The underlying duplicate-question and paraphrase datasets are public and long-standing.",
   "risk": "medium"
  },
  "dataset": {
   "languages": [],
   "license": "Varies by dataset.",
   "modalities": [
    "text"
   ],
   "public_test_set": true,
   "size": 3,
   "size_note": "3 pair-classification datasets in the original MTEB task set, primarily English, including duplicate-question and tweet-paraphrase collections.",
   "splits": "",
   "url": "https://huggingface.co/spaces/mteb/leaderboard"
  },
  "freshness": {
   "researched": "2026-09-07",
   "researched_by": "sonnet-5 agent, batch 1, slice D",
   "reviewed": "",
   "reviewed_by": ""
  },
  "harness": {
   "bigbench": "",
   "helm": "",
   "inspect_evals": "",
   "lm_eval": "",
   "opencompass": "",
   "other": "Run the PairClassification task group in the mteb Python package (pip install mteb; mteb run -t <pair-classification-task-name>)."
  },
  "id": "mteb_pair_classification",
  "last_updated": "",
  "leaderboard_url": "https://huggingface.co/spaces/mteb/leaderboard",
  "lineage": {
   "family": "mteb",
   "predecessor": "",
   "successors": [],
   "variants": []
  },
  "measures": "Pairs of sentences labelled as equivalent or not (paraphrases, duplicate questions) are embedded, and cosine similarity between each pair is used as a ranking score rather than a fixed threshold, evaluated by average precision.\n",
  "metric": {
   "baseline_note": "Dot-product and Euclidean-distance variants are also computed; cosine-based average precision is the metric the leaderboard treats as the headline figure.",
   "direction": "higher_is_better",
   "human_baseline": null,
   "max_score": 100,
   "name": "average precision (cosine similarity)",
   "random_baseline": null,
   "unit": "%"
  },
  "name": "MTEB Pair Classification",
  "page_kind": "subset",
  "paper": {
   "arxiv": "2210.07316",
   "title": "MTEB: Massive Text Embedding Benchmark",
   "url": "https://aclanthology.org/2023.eacl-main.148/",
   "year": 2023
  },
  "publisher": {
   "authors": [
    "Niklas Muennighoff",
    "Nouamane Tazi",
    "Lo\u00efc Magne",
    "Nils Reimers"
   ],
   "org": "Hugging Face and Cohere (original authors); maintained today by the open embeddings-benchmark community",
   "url": "https://github.com/embeddings-benchmark"
  },
  "released": "2022-10",
  "repo_url": "https://github.com/embeddings-benchmark/mteb",
  "saturation": {
   "as_of": "",
   "note": "Not established from a source read for this page; only 3 datasets back this task type, so headline scores should be read cautiously regardless.",
   "status": "unknown",
   "top_score": null
  },
  "sources": [
   {
    "accessed": "2026-09-07",
    "title": "MTEB: Massive Text Embedding Benchmark (arXiv preprint)",
    "url": "https://arxiv.org/abs/2210.07316"
   },
   {
    "accessed": "2026-09-07",
    "title": "embeddings-benchmark/mteb GitHub repository",
    "url": "https://github.com/embeddings-benchmark/mteb"
   },
   {
    "accessed": "2026-09-07",
    "title": "MTEB Leaderboard (Hugging Face Space)",
    "url": "https://huggingface.co/spaces/mteb/leaderboard"
   }
  ],
  "status": "active",
  "subcategory": "pair classification",
  "summary": "Labels sentence pairs as duplicates or not from cosine similarity and scores the ranking by average precision, across 3 primarily-English MTEB datasets.",
  "tags": [
   "embedding",
   "pair-classification",
   "deduplication"
  ],
  "task_format": "Embed sentence pairs; rank by cosine similarity; score against binary equivalence labels with average precision."
 }
}