mLateOn tops multilingual ColBERT retrieval with 115M active params, rivals 8B dense models

IgorCarron · x · 2026-08-20

LightOn's mLateOn (115M active / 312M total params) leads multilingual ColBERT-style retrieval on HAKARI-Bench: 65.52 Overall Macro, 8.33 points ahead of runner-up pplx-embed-v1-late-0.6b while using about a quarter of its active parameters. It combines a multilingual mmBERT encoder with ColBERT-style token matching, supports up to 8,192 tokens, and scores 63.33 on MNanoBEIR — between Qwen3-Embedding-8B (62.87) and Nemotron-3-Embed-8B (64.28).

Related event: LightOn's mLateOn Tops Multilingual ColBERT Retrieval Benchmark(2 posts)→

Original post →

More from Research

Research channel →