←Back to NewsAI News/RetrievalmodelRetrievalBenchmarksJina AI's jina-reranker-v3 Ranks 64 Documents Together in One PassJina AI's 0.6B multilingual reranker beats models 10x its size on BEIR by scoring documents jointly in one context window.SourceJina AIPublishedSep 27, 2026, 10:00 AMAuthorAlphaSignal NewsroomRead1 min readJina AI's 0.6B multilingual reranker beats models 10x its size on BEIR by scoring documents jointly in one context window.Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.Read original report ↗Next readsPerplexity · newsPerplexity's Q2D-Web Benchmark Tests AI Search on 190M Real Web DocumentsKaggle · newsLlamaIndex's ExtractBench Catches GPT-5 and Gemini-3 Hitting 0% on Wide SchemasAlphaSignal · paperSTAIR Beats Every RAG Baseline by Reading Documents Like a Table of Contents
