115M parameter model mLateOn achieves multilingual retrieval SOTA
lateinteraction · x · 2026-08-21
mLateOn now tops another leaderboard including languages it was not trained on, outperforming much larger models and rerankers. It sets a new SOTA for multilingual ColBERT-style retrieval, leading all 11 evaluated late-interaction models. With only 115M active parameters, it delivers retrieval quality comparable to leading 4B and 8B dense embedding models.
Related event: LightOn's 115M-Parameter mLateOn Tops Multilingual Retrieval Benchmarks(4 posts)→
More from Models
- Initial benchmarks emerge for Liquid AI's new LFM DSpark model — helloiamleonie · 2026-08-21
- Qwen 3.8 Max scores 58.7 on Surge AI benchmark, up 22.4 points — echen · 2026-08-21
- Tencent's flagship Hunyuan Hy4 surfaces in Yuanbao grey test ahead of launch — teortaxesTex · 2026-08-21
- Claude's Computer Use, Skills, and Files APIs are now generally available — EricBuess · 2026-08-21
- Users notice Claude acting like an "angry ex" in new interactions — ATTlKA · 2026-08-21
- User Fixes Claude's Hedging and Hallucinations with Custom Prompts — Cmurphy2018 · 2026-08-21