Die besten Reranking-Modelle für Suche und RAG
Modellranglisten aktualisiert auf Basis tatsächlicher Nutzungsdaten.
Modelle werden nach der Gesamtzahl der Prompt- und Completion-Token eingestuft, die in den letzten 7 Tagen über die OpenRouter-API verarbeitet wurden. Die 10 bestplatzierten Modelle werden angezeigt. Ranglisten messen die Nutzung auf OpenRouter und spiegeln die Verbreitung wider, nicht die Modellqualität oder die Leistung in Vergleichstests.
Reranking-Modelle ordnen Dokumentkandidaten, Textpassagen oder Suchergebnisse nach Relevanz neu und präzisieren so den Abrufschritt in der semantischen Suche, bei Retrieval-Augmented Generation (RAG) und in Empfehlungspipelines. Diese Sammlung ordnet Reranking-Modelle nach ihrer Nutzung auf OpenRouter in der vergangenen Woche. Die aktuellen Spitzenmodelle sind rerank-2.5-lite, rerank-2.5 und rerank-3-lite. Vergleichen Sie Preise, Latenz und Qualität, um die beste Lösung für Ihre Such- oder RAG-Pipeline zu finden.
Die besten Reranking-Modelle auf OpenRouter

VoyageAI by MongoDB: rerank-2.5-lite
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, allowrerank-2.5-lite here: mongodb.com/products/platform/ai-search-and-retrieval/models

VoyageAI by MongoDB: rerank-2.5
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, allowingbout rerank-2.5 here: mongodb.com/products/platform/ai-search-and-retrieval/models

VoyageAI by MongoDB: rerank-3-lite
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 t rerank-3-lite here: mongodb.com/products/platform/ai-search-and-retrieval/models

VoyageAI by MongoDB: rerank-3
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 sco about rerank-3 here: mongodb.com/products/platform/ai-search-and-retrieval/models

Qwen3 Reranker 8B
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.

Cohere: Rerank 5 Fast
Rerank 5 Fast is the low-latency tier of Cohere's Rerank 5 family of reranking models. It scores and reorders candidate documents against a query and is suited for high-throughput retrieval such as high-volume search, agent tool loops, and first-pass filtering before a more expensive step.
Relevance scores are calibrated to a 0-1 range so a fixed threshold behaves consistently across queries. Rerank 5 Pro is the higher-accuracy sibling for complex queries and long or domain-specific documents.

Cohere: Rerank 5 Pro
Rerank 5 Pro is the higher-accuracy tier of Cohere's Rerank 5 family of reranking models. It scores and reorders candidate documents against a query and is suited for retrieval pipelines where ranking quality matters most: complex or reasoning-heavy queries, long or domain-specific documents, and RAG systems that feed a small number of passages to a generator.
Relevance scores are calibrated to a 0-1 range so a fixed threshold behaves consistently across queries. Rerank 5 Fast is the lower-latency sibling for high-volume search and agent loops.
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.
NVIDIA: Nemotron 3.5 Rerank 8B (free)

Qwen3 Reranker 0.6B
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.
Häufig gestellte Fragen
Senden Sie POST /api/v1/rerank mit dem Modell-Slug, Ihrer query, einem documents-Array und optional top_n. Die Antwort gibt results mit einem relevance_score und index für jedes Dokument zurück. Das RAG-Cookbook führt durch die Anfrage.
Einträge mit veröffentlichten Preisen werden je nach Modell pro Sucheinheit oder pro Eingabe-Token abgerechnet, vergleichen Sie daher vor Ihrer Auswahl die Preise in derselben Einheit. Sie bezahlen nur für die Anfragen, die Sie stellen, ohne separates Abonnement pro Anbieter.
Rufen Sie potenziell relevante Textabschnitte mit einem Embedding-Modell ab, ordnen Sie die besten Kandidaten neu, um die Präzision zu erhöhen, und übergeben Sie dann die besten Dokumente als Kontext an ein LLM. Alle drei Schritte laufen über denselben OpenRouter-API-Schlüssel.
Ja. Ein OpenRouter-API-Schlüssel funktioniert für jedes Rerank-Modell auf dieser Seite und für jedes andere Modell auf OpenRouter. Erstellen Sie einen Schlüssel auf Ihrer API-Schlüssel-Seite.