jev-reranker edges out ruri-v3 on four of five Japanese retrieval benchmarks
amaarora · x · 2026-09-21
hotchpotch benchmarked jev-reranker against the strong Japanese reranker ruri-v3-reranker-m310 across five NanoJMTEB tasks. Jev trails clearly on JaCWIR but edges ahead on the other four tasks in nDCG@10. At a 0.2 threshold it also filters out 84-97% of retrieved documents.
More from Models
- Tokenmaxxing debate: routers may accelerate open model revenue, says xeophon — xeophon · 2026-09-21
- Will ChatGPT merge chat and work modes like Claude — and what happens to limits? — koltregaskes · 2026-09-21
- Agents feel less reliable since September model updates, devs log failure rates to find out — john_snow_21 · 2026-09-21
- Report: DeepSeek training a 2T-param model with 8T planned, Huawei chips due late 2026 — Hesamation · 2026-09-21
- Codex PRO+ Users Report Usage Draining Much Faster Since Weekly Reset — Next_Technology6361 · 2026-09-21
- Open-source finetune project laya hits 6.9k stars with free Kaggle 2xT4 notebook — ojasvi_yadav · 2026-09-21