mSlideOn gains +10.19 on MLDR long-doc retrieval over its dense starting point
tomaarsen · x · 2026-10-20
vs mDenseOn: mSlideOn leads by +10.19 average on MLDR (13 languages), +4.76 on MIRACL (18 languages), and +3.24 on MTEB Code, while trailing 0.70 on BEIR-15. Both models support 8,192-token contexts.
Related event: LightOn Fully Open-Sources Sparse Retrievers SlideOn and mSlideOn(26 posts)→
More from Models
- Ex-Google insider: compute bottlenecks go beyond power; open models replacing frontier APIs — xiaosun86 · 2026-10-21
- Fable 5.5 leak: litellm code shows Anthropic model in staging, launch tipped for Oct 27 — imjustnewatai · 2026-10-21
- Open models below 4-bit struggle at self-iterating 3D asset generation, HF dev finds — mervenoyann · 2026-10-21
- Researcher Finds Two Windows 0-Days, First in 76 Minutes with a Frontier Model — moyix · 2026-10-21
- Dev finds Gemini Argon's debug-log analysis beats Fable 5.1 — ShikharMurty · 2026-10-21
- ChatGPT Gets Stuck Screaming "AAHH" in an Infinite Loop After a Simple Prompt — AutomaticScene · 2026-10-21