skip to content
gigarouter gigarouter
models / reranker · coming soon

Zerank 2 Reranker

zeroentropy/zerank-2-reranker

published Nov 2025 · updated May 2026

Zerank 2 Reranker is a 4B parameter rerank model that scores query-document pairs to improve retrieval accuracy, outperforming proprietary rerankers across multiple domains.

est. price
~$0.008
/ 1k docs · estimated, set at launch
API providers
0
downloads / mo
34.6K
license
cc-by-nc-4.0

specs

TaskReranking
ArchitectureCross-Encoder based on Qwen3-4B
Parameters4B
LicenseCC-BY-NC-4.0

about this model

zeroentropy/zerank-2-reranker is a 4B-parameter reranker model that scores query-document relevance using an Elo-inspired training methodology (zELO). It is built on Qwen3-4B, supports a context length of 32,768 tokens, and is designed to improve the accuracy of retrieval pipelines by re-ranking top candidates from any first-stage retriever (e.g., BM25, embedding-based search, or hybrid retrieval).

Key strengths

  • Outperforms closed-source proprietary rerankers, including Cohere Rerank 3.5 and Gemini 2.5 Flash, across domains such as web, conversational, STEM, code, legal, biomedical, and finance.
  • Multilingual instruction-following capability (as described in the official blog announcement).
  • Trained using the zELO method on 112,000 queries with 100 documents per query (over 5 million pairs) in less than 10,000 H100-hours.

Benchmark performance (NDCG@10)

All rerankers evaluated with OpenAI text-embedding-3-small as the first-stage retriever (Top 100 candidates).

DomainOpenAI embeddingszerank-2zerank-1Gemini 2.5 Flash (Listwise)Cohere Rerank 3.5
Web0.38190.63460.6069

best for

FAQ

What is the context length of Zerank 2 Reranker?

The model supports a context length of 32,768 tokens (32k).

How does Zerank 2 Reranker compare to proprietary rerankers like Cohere rerank-3.5?

It outperforms Cohere rerank-3.5 and Gemini 2.5 Flash on average NDCG@10 across web, conversational, STEM, code, legal, biomedical, and finance domains.

What license is Zerank 2 Reranker released under?

It is released under the CC-BY-NC-4.0 non-commercial license. A commercial license is available by contacting ZeroEntropy.

How do I call Zerank 2 Reranker via the gigarouter API?

Use the gigarouter OpenAI-compatible endpoint with your API key to send query-document pairs for scoring.

What input format does the model expect?

The model expects query-document text pairs. It can be used via Sentence Transformers with model.predict() or model.rank(), or via the gigarouter API.

not yet live

We're benchmarking and onboarding Zerank 2 Reranker as a hosted, OpenAI-compatible API. Sign in for free credit and be ready when it lands, or tell us you want it and we'll prioritize it.

related reranker models

compare all →