Jina releases a 0.6B reranker that matches 4B models on BEIR
_reachsumit · x · 2026-07-21
- Jina AI released jina-reranker-v3.5, a 0.6B listwise reranker.
- It uses hybrid sliding-window + global attention and self-distillation.
- The model reportedly matches 4B-class models on BEIR despite its much smaller size.
- The post links both the paper and the Hugging Face model, indicating this is a concrete model release rather than a vague announcement.
More from Models
- Rumor claims Kimi faked performance by serving Claude; DeepSeek new model surprises in evals — realsohamparekh · 2026-09-11
- GPT-5.6 writes well but is instantly forgettable, user complains — BasedRaddka · 2026-09-11
- Opus Refuses Protein Research Codebase Over 'Safety' Concerns, Dev Considers Rolling His Own — josephdviviano · 2026-09-11
- User Hails Unconfirmed 'DeepSeek 4.1 Flash' as an Inflection Point in LLMs — himanshustwts · 2026-09-11
- Terminal Bench v4: GLM-5.3 Leads at 41.9%, Kimi-K3 Underwhelms at 12.6% — Ok_Warning2146 · 2026-09-11
- GPT-6 Astra beats Factorio with enemies in 44 in-game hours at ~$4,500 API cost — liminal_bardo · 2026-09-11