Liquid AI's LongevityBench: compact LFMs beat frontier models on several aging tasks
JosephJacks_ · x · 2026-10-01
Liquid AI and InSilico Medicine launched LongevityBench, a new aging benchmark testing models on 17 tasks across clinical records, DNA methylation, transcriptomics, proteomics, and genetics.
On several tasks, Liquid AI's compact LFMs outperformed every frontier model evaluated. Researcher Katerina Nasto and CTO Mathias Lechner discuss how the benchmark was built, why leakage-proof evaluation matters, and how specialized models running locally on sensitive patient data could help researchers move from prediction to better hypotheses and experiments.
The team will present at the ARDD longevity meeting this week; blog, model, and paper are available.
More from Models
- 27B at Q5 with full 131k context on one 24GB RTX 3090, 13-17% faster — bjivanovich · 2026-10-01
- Sol 6.1 Day Two Impressions: Strong at Scheduled Tasks and Data Analysis, Cheap — bindureddy · 2026-10-01
- OpenCode's Free Stealth Model Gives Trillions of Tokens Daily, Tested With Blender MCP — sidahuj · 2026-10-01
- Block AttnRes analysis: a quarter of layers dead at depth 32, peak mixing at 20 layers — ziv_ravid · 2026-10-01
- Claude took on the Riemann Hypothesis — here's what actually happened — elsleightholm · 2026-10-01
- GPT-6.1 Sol coming soon to ChatGPT's regular chat mode — mark_k · 2026-10-01