tech
jina-reranker-v3.5: Faster Listwise Reranking with Hybrid Attention and Self-Distillation
Today we release jina-reranker-v3.5, a 0.6B-parameter listwise reranker that keeps the last but not late interaction of jina-reranker-v3 and makes it faster and far more capable on the data enterprises actually search. It reaches 63.20 nDCG@10 on BEIR, ahead of Qwen3-Reranker-4B with roughly 7× fewer parameters, and it reranks up to 1.56× faster than v3 on long documents. Its biggest jump is on semi-structured retrieval: +9.6 nDCG@10 over v3 on field-constrained records.
TL;DR
- Jina-reranker-v3.5 is a new 0.6B-parameter listwise reranker.
- It is faster and more capable than jina-reranker-v3 on enterprise search data.
- Achieves 63.20 nDCG@10 on BEIR, surpassing Qwen3-Reranker-4B with fewer parameters.
- Reranks up to 1.56x faster than v3 on long documents.
- Shows a +9.6 nDCG@10 improvement on semi-structured retrieval over v3.