Cohere Rerank 5 Pro: calibrated 0–1 relevance scores for consistent RAG thresholds
cohere · x · 2026-11-04
Cohere details its Rerank 5 reranking family, now live on OpenRouter alongside Embed 5.
- Rerank 5 Pro scores and reorders candidate documents against a query, targeting pipelines where ranking quality matters most: complex or reasoning-heavy queries, long/domain-specific documents, and RAG systems feeding a generator a small number of passages. Relevance scores are calibrated to a 0–1 range so fixed thresholds behave consistently across queries; priced at $0.05/M tokens with 33K context.
- Rerank 5 Fast is the lower-latency sibling for high-volume search and agent loops.
Related event: Cohere Embed 5 and Rerank 5 land on OpenRouter(4 posts)→
More from Models
- AI semiotics: models are swayed by visual symbols without recognizing it in their chains-of-thought — emollick · 2026-11-05
- Kimi K3.1 Pro hits 61.2% on long-horizon code bench, up from 55.95% — vllm_project · 2026-11-05
- Liquid AI: vision encoders can burn more compute than the LLM on large images and video — JosephJacks_ · 2026-11-05
- Baseten explains how to make flash models faster: kernel fusion, PDL, and host loop cuts — baseten · 2026-11-05
- Moonshot AI open-sources Kimi K3.1 Pro: 2.8T-param MoE with 1M-token context — Kimi_Moonshot · 2026-11-05
- Tencent launches Hy4: first Hunyuan model with native vision and computer use — Aiden_Tech_Ai · 2026-11-04