jina-ai/jina-reranker-v3.5 ↗
$0.05
- Inference provider
- jina
- Platform
- Jina AI
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
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 que…
jina/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.
1–1 / 1
$0.05
1–1 / 1
1–1 / 1
1–6 / 6
1–2 / 2
These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.