# v3.5

Published articles for v3.5.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## rerank-2.5 and rerank-2.5-lite: instruction-following rerankers

DevFeed: [rerank-2.5 and rerank-2.5-lite: instruction-following rerankers](<https://devfeed.tech/articles/rerank-2-5-and-rerank-2-5-lite-instruction-following-rerankers-82919.md>)

Original publisher: [Read original article](<https://blog.voyageai.com/2025/08/11/rerank-2-5/>)

Author: Voyage AI

Published: 2025-08-11T07:00:00Z

Content type: release

Language: en

Sources: [Voyage AI](<https://devfeed.tech/sources/voyage-ai.md>)

Topics: [AI-driven information retrieval](<https://devfeed.tech/topics/ai-driven-information-retrieval.md>), [ai-experiments](<https://devfeed.tech/topics/ai-experiments.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [cohere](<https://devfeed.tech/tags/cohere.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [news](<https://devfeed.tech/tags/news.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [v3-5](<https://devfeed.tech/tags/v3-5.md>)

### AI overview

Voyage AI announces rerank-2.5 and rerank-2.5-lite, rerankers that add natural-language instruction following and support a 32K-token context. The article reports accuracy improvements over Cohere Rerank v3.5 across its evaluation datasets and describes how instructions can steer relevance scoring for retrieval applications.

### Source excerpt

TL;DR - We are excited to introduce the rerank-2.5 series, which significantly improves upon rerank-2's performance while also introducing instruction-following capabilities for the first time. On our standard suite of 93 retrieval datasets spanning multiple domains, rerank-2.5 and rerank-2.5-lite improve retrieval accuracy by 7.94% and 7.16% over Cohere Rerank v3.5. Furthermore, the new instruction-following feature [...]