Best Rerank Models for Search and RAG
Model rankings updated August 2026 based on real usage data.
Rerank models reorder candidate documents, passages, or search results by relevance, sharpening the retrieval step in semantic search, retrieval-augmented generation (RAG), and recommendation pipelines. This collection ranks reranking models by their usage on OpenRouter over the past week. The current top models are Llama Nemotron Rerank VL 1B V2 (free), rerank-2.5, and rerank-2.5-lite. Compare pricing, latency, and quality to find the best fit for your search or RAG pipeline.
Top Rerank Models on OpenRouter
NVIDIA: Llama Nemotron Rerank VL 1B V2 (free)
14.6B tokens
Llama Nemotron Rerank VL 1B V2 is a 1.7B multimodal reranking model from NVIDIA. It evaluates the relevance of document images and text against user queries, designed for vision RAG pipelines handling charts, tables, infographics, and mixed-media documents. Functions as a cross-encoder that accepts text queries paired with image, text, or combined document inputs, delivering approximately 6-7% recall improvements over embedding-only baselines on visual document retrieval benchmarks.
VoyageAI by MongoDB: rerank-2.5
2.05B tokens
rerank-2.5 is a cutting-edge reranker optimized for quality, delivering a 7.94% improvement in retrieval accuracy over Cohere Rerank v3.5 across 93 datasets. It also outperformed Cohere Rerank v3.5 by 12.70% on the Massive Instructed Retrieval Benchmark (MAIR). The model supports a combined context length of 32K tokens per query–document pair, including up to 8K tokens for the query, enabling more accurate retrieval over longer documents. Additionally, rerank-2.5 supports instruction following, allowing users to guide relevance scoring through natural language prompts. Learn more about rerank-2.5 here: https://blog.voyageai.com/2025/08/11/rerank-2-5
VoyageAI by MongoDB: rerank-2.5-lite
1.83B tokens
rerank-2.5-lite is a reranker optimized for both latency and quality, delivering a 7.16% improvement in retrieval accuracy over Cohere Rerank v3.5 across 93 datasets. It also outperformed Cohere Rerank v3.5 by 10.36% on the Massive Instructed Retrieval Benchmark (MAIR). The model supports a combined context length of 32K tokens per query–document pair, including up to 8K tokens for the query, enabling more accurate retrieval over longer documents. Additionally, rerank-2.5-lite supports instruction following, allowing users to guide relevance scoring through natural language prompts. Learn more about rerank-2.5-lite here: blog.voyageai.com/2025/08/11/rerank-2-5
Cohere's AI search foundation model for enhancing the relevance of information surfaced within search and RAG systems. Features a 32K context window, multilingual support across 100+ languages, no data pre-processing required, and state of the art performance with low latency.
Cohere's AI search foundation model for enhancing the relevance of information surfaced within search and RAG systems. Features a 32K context window, multilingual support across 100+ languages, no data pre-processing required, and high performance with lowest latency.
Rerank v3.5 is designed to reorder search results for improved relevance. It supports multi-aspect and semi-structured data reranking over 100+ languages. Ideal for refining results from semantic or keyword search pipelines.