ZeroEntropy

weights

open(Apache-2.0 ungated safetensors for zerank-1, zerank-1-small and zerank-2)

data

closed(the Elo-based relevance pipeline is described in arXiv 2509.12541

code

closed(no training or model repository

license

Apache-2.0(OSI)

Both zerank-2 and the earlier zerank-1 line are released under Apache-2.0, confirmed in the card and in ZeroEntropy's announcement of the Notion acquisition, which states that all its models are now open source under Apache-2.0. Neither the training data nor any training or model repository is released, so the release stays open weights rather than open source.

• https://huggingface.co/zeroentropy/zerank-1-reranker/raw/main/README.md recorded 2026-10-13

  Front matter for zerank-1 also reads license: apache-2.0, confirming the terms are consistent across the distributed SKUs rather than new with zerank-2.

• https://huggingface.co/zeroentropy/zerank-2-reranker/raw/main/README.md recorded 2026-10-13

  Front matter reads license: apache-2.0, base_model Qwen/Qwen3-4B; the Model Details table records License Apache-2.0 and the closing License section repeats it. Training is described as a multi-stage Elo-rating pipeline with a link to arXiv 2509.12541; no corpus or training code is offered.

• https://zeroentropy.dev/articles/zeroentropy-is-joining-notion/ recorded 2026-10-13

  ZeroEntropy announcement dated 2026-07-24: "ZeroEntropy has been acquired by Notion", "All of our models are now fully open-source under Apache 2.0", and all ZeroEntropy products remain supported until September 4th, 2026 after which they are sunset.

Adoption is measured as Hugging Face downloads across the zerank line, almost all of it for zerank-2, with much smaller shares for zerank-1-small and zerank-1.

• https://huggingface.co/api/models/zeroentropy/zerank-2-reranker recorded 2026-09-11

  downloads: 644922; gated: false; private: false; license apache-2.0 for zeroentropy/zerank-2-reranker.

Zerank-2 is a current 4B model that beats the named proprietary rerankers on ZeroEntropy's own seven-domain suite, putting it at the frontier alongside jina-reranker, the other current-generation line here. Confidence stays medium because that evaluation is a vendor-built suite with no public leaderboard behind it, unlike BEIR or MMTEB.

• https://huggingface.co/zeroentropy/zerank-2-reranker/raw/main/README.md recorded 2026-09-11

  Evaluations table gives zerank-2 an average NDCG@10 of 0.6714 across seven domains against 0.6456 for zerank-1, 0.5999 for Gemini 2.5 Flash listwise, 0.5847 for Cohere rerank-3.5 and 0.4509 for the OpenAI embedding retriever alone; 4B parameters, 32,768-token context.