{"version":1,"type":"story","url":"https://digestai.news/story/cohere-releases-rerank-5-with-passage-level-context-focus-and-calibrat","json":"https://digestai.news/story/cohere-releases-rerank-5-with-passage-level-context-focus-and-calibrat.json","markdown":"https://digestai.news/story/cohere-releases-rerank-5-with-passage-level-context-focus-and-calibrat.md","slug":"cohere-releases-rerank-5-with-passage-level-context-focus-and-calibrat","headline":"Cohere releases Rerank 5 with passage-level context focus and calibrated scores","summary":"Cohere AI announced Rerank 5, a retrieval‑reranking model offered in Pro and Fast tiers. Both versions run on a 32K token context window, support over 100 languages and can be accessed via the Cohere API, Model Vault, Microsoft Foundry, Amazon SageMaker, private VPC or on‑prem. The update adds an optional Context Focus feature that returns scored character spans inside each document, and calibrated relevance scores that read as probabilities.\n\nCohere reports that the Pro tier ranks first on 39 of 46 composite datasets and scores 82.2 on the BRIGHT benchmark, 5.8 points above Voyage AI Rerank 3. Median latency is 11.7 s per 96‑document request versus 4.1 s for Fast. In internal tests, Context Focus cut tokens by 19 % to 34 % while keeping 57 %‑58 % answer accuracy, and reduced tokens by 41 % on deep‑search benchmarks with accuracy rising from 39 % to 52 %. Calibrated scores achieve an expected calibration error of about 0.06. Pricing is $0.05 per 1 M tokens for Pro and $0.02 for Fast, with Model Vault instances at $4.00 per hour. Integrations include LangChain, Haystack, Elasticsearch and Weaviate. All benchmark figures are self‑reported by Cohere and have not been independently verified.","keyPoints":["Pro version tops 39 of 46 composite datasets and scores 82.2 on BRIGHT, 5.8 points above Voyage AI Rerank 3.","Context Focus can cut tokens by 19‑34% while keeping 57‑58% accuracy, and up to 41% token reduction on deep‑search benchmarks.","API pricing is $0.05 per 1M tokens for Pro and $0.02 for Fast; both offer a 32K token window."],"whyItMatters":"Rerank 5 lets developers send fewer, higher‑quality tokens to LLMs, lowering latency and cost for retrieval‑augmented generation and agent pipelines, while offering calibrated scores for better relevance filtering.","category":{"slug":"models","name":"Generative AI & Models","url":"https://digestai.news/category/models"},"entities":{"companies":["Cohere AI","Voyage AI","Microsoft","Amazon","NVIDIA","LangChain"],"models":["Rerank 5 Pro","Rerank 5 Fast","Voyage AI Rerank 3","Rerank 4 Pro","Qwen3‑Reranker‑8B"],"people":["Michal Sutter"]},"firstPublishedAt":"2026-10-22T16:31:31Z","updatedAt":"2026-10-22T16:31:31Z","sourceCount":1,"hasPrimarySource":false,"sources":[{"outlet":"MarkTechPost","title":"Cohere Releases Rerank 5 With Passage-Level Context Focus and Calibrated Scores","url":"https://marktechpost.com/2026/10/22/cohere-rerank-5-context-focus","publishedAt":"2026-10-22T16:31:31Z","type":"press","primary":false,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"Cohere releases Rerank 5 with passage-level context focus and calibrated scores\", 22 October 2026, https://digestai.news/story/cohere-releases-rerank-5-with-passage-level-context-focus-and-calibrat","publisher":"Digest AI","title":"Cohere releases Rerank 5 with passage-level context focus and calibrated scores","datePublished":"2026-10-22T16:31:31Z","url":"https://digestai.news/story/cohere-releases-rerank-5-with-passage-level-context-focus-and-calibrat"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}