mxbai-rerank

Open weights · mixedbread-ai · Updated 26 Sep 2026

mixedbread-ai ships two generations of reranker. v1 (xsmall/base/large) is a DeBERTa-v3 cross-encoder family, English-only, and its xsmall variant is compact enough to run in the browser — which is why it's one of the options in this site's live demo. v2 (base/large) is a newer, Qwen2.5-based, RL-trained generation that adds support for 100+ languages, including Chinese. Both generations ship under Apache 2.0.

Model variants

The v1 family are DeBERTa-v3 cross-encoders trained on MS MARCO passage ranking; v2 is a Qwen2.5-based generation trained with a three-step reinforcement-learning process (GRPO, contrastive learning, preference learning). Start with mxbai-rerank-base-v2 for new production use, especially with any non-English content — it beats v1's large on every published benchmark below. Keep xsmall-v1 only for browser or edge deployments, since v2 has no comparably small variant.

Benchmarks

Rows marked * are from mixedbread's own cross-generation comparison table (mxbai-rerank on GitHub), not the classic BEIR 18-dataset suite. Until September 2026 this page carried large-v1 at an unsourced ~62.1 — mixedbread's own launch blog reported ~48.8 NDCG@10 on 11 BEIR datasets, and their 2026 comparison table reports 49.32*; both are far below the number this page previously carried, so it's now corrected. The xsmall-v1/base-v1 rows and the MS MARCO column remain approximate figures we haven't independently re-verified — check the mixedbread-ai HuggingFace model cards for authoritative per-dataset results.

Multilingual (why v2 exists)

v1 was never a multilingual model — it just hadn't been benchmarked on non-English data until mixedbread's own 2026 retrospective. If your documents aren't all English, v2 is the generation to use; v1 is not a substitute.

Quick start

v2, self-hosted

pip install -U mxbai-rerank

from mxbai_rerank import MxbaiRerankV2

reranker = MxbaiRerankV2("mixedbread-ai/mxbai-rerank-base-v2")  # or large-v2

query = "How do I add reranking to my RAG pipeline?"
documents = [
    "Rerankers score each query-passage pair with a cross-encoder.",
    "BM25 is a classical keyword-based retrieval method.",
    "London is the capital of the United Kingdom.",
    "Two-stage retrieval: retrieve 50 candidates, rerank to top 5.",
]

results = reranker.rank(query=query, documents=documents)
for r in results:
    print(f"{r.score:.4f}  {r.document[:80]}")

v1, self-hosted (sentence-transformers)

pip install sentence-transformers

from sentence_transformers import CrossEncoder

model = CrossEncoder("mixedbread-ai/mxbai-rerank-base-v1")

query = "How do I add reranking to my RAG pipeline?"
passages = [
    "Rerankers score each query-passage pair with a cross-encoder.",
    "BM25 is a classical keyword-based retrieval method.",
    "London is the capital of the United Kingdom.",
    "Two-stage retrieval: retrieve 50 candidates, rerank to top 5.",
]

scores = model.predict([(query, p) for p in passages])
ranked = sorted(zip(scores, passages), reverse=True)

for score, text in ranked:
    print(f"{score:.4f}  {text[:80]}")

In a RAG pipeline (v2)

from mxbai_rerank import MxbaiRerankV2

reranker = MxbaiRerankV2("mixedbread-ai/mxbai-rerank-large-v2")

def rag_answer(query: str, vector_db, llm) -> str:
    # Stage 1: retrieve wide
    candidates = vector_db.search(query, top_k=50)
    # Stage 2: rerank tight
    results = reranker.rank(query=query, documents=candidates, top_k=5)
    top5 = [r.document for r in results]
    # Stage 3: generate
    return llm.complete(f"Context:\n" + "\n\n".join(top5) + f"\n\nQ: {query}")

Hosted API

mixedbread-ai offers a hosted rerank endpoint backed by the same model weights. Useful if you want to avoid running inference on your own infrastructure. The current SDK is mixedbread (the older mixedbread_ai package was v1-era):

pip install mixedbread

from mixedbread import Mixedbread

mxbai = Mixedbread(api_key="YOUR_API_KEY")

result = mxbai.rerank(
    model="mixedbread-ai/mxbai-rerank-large-v2",
    query="How do I add reranking to my RAG pipeline?",
    input=[
        "Rerankers score each query-passage pair jointly.",
        "BM25 is a keyword-based retrieval method.",
        "London is the capital of the United Kingdom.",
        "Two-stage retrieval: retrieve wide, rerank tight.",
    ],
    top_k=3,
)

for item in result.data:
    print(f"{item.score:.4f}  rank {item.index + 1}")

Browser use

The v1 xsmall variant is compact enough to run in the browser via transformers.js — this is exactly what our demo uses. v2's smallest variant (0.5B) has no equivalent browser-sized build yet:

// transformers.js (ES module)
import { AutoTokenizer, AutoModelForSequenceClassification }
  from "https://cdn.jsdelivr.net/npm/@huggingface/transformers@4";

const tokenizer = await AutoTokenizer.from_pretrained(
  "mixedbread-ai/mxbai-rerank-xsmall-v1", { dtype: "q8" }
);
const model = await AutoModelForSequenceClassification.from_pretrained(
  "mixedbread-ai/mxbai-rerank-xsmall-v1", { dtype: "q8" }
);

const inputs = tokenizer(
  [query, query],
  { text_pair: [doc1, doc2], padding: true, truncation: true }
);
const { logits } = await model(inputs);
const scores = logits.sigmoid().tolist();

With dtype: "q8" the quantized weights are roughly 35 MB — fast to download and cached in IndexedDB after the first run.

Pros and cons

Other models