Cohere has launched Rerank 4, the most advanced set of reranker models available, purpose-built to meet the realities and challenges of enterprise AI search.
Rerank 4 delivers best-in-class retrieval, outperforming MongoDB's Voyage models and ElasticSearch's Jina rerankers in overall search relevance, as well as improved latency, flexible deployment options, deep customizability, and robust multilingual performance. Designed for business-critical applications across key industries and domains, Rerank 4 sets a new standard for accuracy and adaptability in enterprise search.
The new reranker significantly enhances the accuracy of enterprise AI search by refining initial retrieval results. After a fast but broad candidate-generation step using methods like BM25 or bi-encoder embeddings, the system is left with documents, passages, or product listings that approximate relevance but often miss the nuance of user intent. Rerank 4 addresses this gap using a cross-encoder architecture that processes queries and candidates jointly, capturing subtle semantic relationships and reordering results to surface the most relevant items.
Rerank 4 boasts a 32K context window, the largest of Cohere's Rerank series to date and a four-fold increase over the previous generation. This enables the model to handle longer documents, evaluate multiple passages simultaneously, and capture relationships across sections that shorter windows would miss. This expanded capacity improves ranking accuracy for realistic document types and increases confidence in the relevance of retrieved results.
To support different search workloads, Rerank 4 is available in two versions. Fast is a smaller model designed for use cases where both speed and accuracy are important, suitable for e-commerce product recommendations, programming documentation reference, and customer service ticket triage. Pro is optimized for tasks that require deeper reasoning and analysis, ideal for finance risk modeling, healthcare clinical review, and manufacturing quality engineering.
Benchmarking against industry standards confirms that Rerank 4 outperforms all current competitive alternatives in a broad array of enterprise domains, such as finance, healthcare, and manufacturing. The model also leads in multilingual performance, with users able to deploy Rerank in over 100 world languages, including state-of-the-art retrieval in 10 major business languages.
Rerank 4 is Cohere's first reranking model with self-learning capability. In partnership with Cohere, users can customize their model for certain use cases without the need for further annotated data. With automated adaptation to domain-specific use cases, the accuracy of Rerank 4 Fast iteratively improves to become competitive with much larger market alternatives.
Related reading
- Cohere and SAP plan to deliver sovereign AI solutions in Europe
- Cohere launches Partner Program to accelerate enterprise AI adoption
Rerank 4 is a key component of North, Cohere's agentic AI platform, which combines intelligent search, large language models, and customizable AI agents to automate tasks and accelerate decision-making. It integrates seamlessly into existing AI search solutions, including hybrid, vector, and keyword-based systems, with minimal code changes.
Rerank 4 is now available on Cohere's Platform, Amazon SageMaker AI (Fast & Pro), and Microsoft Foundry, with additional platform support coming soon.