Nagoya University's Ruri v3 Beats OpenAI Embeddings on Japanese Retrieval

A 315M-parameter Japanese embedding model built on ModernBERT-Ja tops JMTEB benchmarks while handling 8K context, outperforming OpenAI and billion-parameter rivals.

Read the full story at AlphaSignal ↗

Timeline · 1 report

2026-10-15 09:29 · AlphaSignal
Nagoya University's Ruri v3 Beats OpenAI Embeddings on Japanese Retrieval

More stories

Eight US states sue OpenAI over alleged child safety violations — The Verge AI
OpenAI alleges ex-employee took confidential files to Apple — The Verge AI
FBI arrests former OpenAI employee for allegedly planting recording device — Sky News Technology
Gemini 4 Argon: Built to solve your hardest problems — Google AI Blog
Cooking up a catering business with ChatGPT — OpenAI YouTube
Amp integrates OpenAI models to expand AI agent capabilities beyond coding — OpenAI News
SentinelOne Reduces Malware Analysis Time to Hours Using OpenAI Daybreak — OpenAI News
A New Report Sheds Light on the Secretive Race to Build Self-Improving AI — TIME Tech

Get the daily brief of stories like this at 6:30 every morning →