Jina AI · Rerank
Jina Reranker v3.5
jina-reranker-v3.5 is a 0.6B parameter multilingual listwise document reranker and a drop-in upgrade to jina-reranker-v3. It keeps the same last-but-not-late (LBNL) listwise interface — ranking a query against many candidates in a single forward pass — while improving domain robustness, structured-data ranking, multilingual retrieval, and inference efficiency. Built on Qwen3-0.6B with 28 layers using hybrid 3L2G attention (sliding-window layers, window 1024, interleaved with global-attention layers and a pinned terminal global layer required by LBNL) and a lightweight MLP projector (1024→512→512), it supports up to 131K tokens of context and ranks documents jointly via causal self-attention and cosine scoring. It reaches 63.20 nDCG@10 on BEIR — above the 4B Qwen3-Reranker at roughly 7× fewer parameters — while running 1.22×–1.56× faster than v3 across short-to-long contexts.
Evidence and sources
Advantages and trade-offs
Compared with 10 representative rerank models
Advantages
Input & output
as stated by the model's providersLike this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works