검색 및 RAG를 위한 최고의 리랭크 모델
모델 순위가 실제 사용 데이터를 기반으로 업데이트되었습니다.
모델은 최근 7일 동안 OpenRouter API를 통해 처리된 총 프롬프트 및 완료 토큰 수를 기준으로 순위가 매겨집니다. 활성 엔드포인트가 없는 모델은 동일한 사용량 순서로 가장 마지막에 표시됩니다. 상위 10개 모델을 표시합니다. 순위는 OpenRouter에서의 사용량을 측정하며, 모델 품질이나 벤치마크 성능이 아닌 도입 정도를 반영합니다.
리랭크 모델은 후보 문서, 구절 또는 검색 결과를 관련성에 따라 다시 정렬하여 시맨틱 검색, 검색 증강 생성(RAG), 추천 파이프라인의 검색 단계를 개선합니다. 이 컬렉션은 지난주 OpenRouter에서의 사용량을 기준으로 리랭킹 모델의 순위를 매깁니다. 현재 상위 모델은 rerank-2.5-lite, rerank-2.5 및 rerank-3-lite입니다. 가격, 지연 시간, 품질을 비교하여 검색 또는 RAG 파이프라인에 가장 적합한 항목을 찾으십시오.
OpenRouter의 최고의 리랭크 모델
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
VoyageAI by MongoDB: rerank-2.5
36.1B 토큰
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
rerank-3-lite is a reranker optimized for both latency and quality and a drop-in upgrade to rerank-2.5-lite, improving on it by 0.94% NDCG@10 on average across domain evaluations and by 1.86% on long-document evaluations, with code retrieval gains of 2.77% atop voyage-3-large and 2.59% atop voyage-4-large. It matches the retrieval quality of rerank-2.5, and across 93 retrieval datasets it outperforms Cohere Rerank v4.0 Pro by 1.44% and Qwen3-Reranker-8B by 2.61%. 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-3-lite supports instruction following, allowing users to guide relevance scoring through natural language prompts. Learn more about rerank-3-lite here: blog.voyageai.com/2026/09/30/rerank-3
Qwen3 Reranker 8B
9.25B 토큰
Qwen3 Reranker 8B is a text reranking model from Alibaba Cloud built on the Qwen3 architecture. It evaluates query-document pairs to produce relevance scores for use in retrieval and RAG pipelines. Supports 100+ languages and programming languages, with instruction-aware reranking that allows customizing scoring criteria per task. Offers strong performance on multilingual benchmarks including MTEB, CMTEB, and MMTEB.
rerank-3 is a reranker optimized for quality and a drop-in upgrade to rerank-2.5, improving on it by 0.80% NDCG@10 on average across domain evaluations and by 3.35% on long-document evaluations, with code retrieval gains of 2.01% atop voyage-3-large and 1.96% atop voyage-4-large. Across 93 retrieval datasets it outperforms Cohere Rerank v4.0 Pro by 2.14% and Qwen3-Reranker-8B by 3.31%. 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-3 supports instruction following, allowing users to guide relevance scoring through natural language prompts. Learn more about rerank-3 here: blog.voyageai.com/2026/09/30/rerank-3
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.
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.
Qwen3 Reranker 0.6B is the smallest text reranking model from Alibaba Cloud in the Qwen3 Reranker series. Built on the Qwen3 architecture, it evaluates query-document pairs to produce relevance scores for retrieval and RAG pipelines. Supports 100+ languages with instruction-aware reranking. Designed for low-latency, resource-constrained deployments.