# Ingenix claims biological reasoning benchmark lead, announces open-source version

_Published Monday, November 9, 2026 at 4:18 AM EST · AI · Latest · Tier 2 — Notable_

![Ingenix claims biological reasoning benchmark lead, announces open-source version — Primary](https://s.yimg.com/lo/mysterio/api/d262ec76922b0da04b2a6dc77eabae03d0241d0bdf3d7ff7b39d13b7e7013559/lightyear_networkapi/resizefill_w1200%3Bquality_80%3Bformat_webp/https%3A%2F%2Fmedia.zenfs.com%2Fen%2Fprnewswire.com%2F61887d33282f7c47141ce65422b38757.jpg)

Ingenix says its 9-billion-parameter Thalamus Reasoning model ranks first among 29 models on LongevityBench, which tests language models on cellular aging research. The Polish company announced it would release an open-source version, Thalamus Decision, on November 9 for academic and commercial researchers to inspect, reproduce and build on.

The model converts methylation, expression and proteomics data into mathematical vectors, using four tokens per biological profile. Ingenix reports DNA methylation age error of 3.36 years, compared with 12.9 years for the best text-prompted model using the same Qwen3.5-9B base. The reported benchmark results concern Thalamus Reasoning; the announced open-source version is Thalamus Decision.

## Sources

- [Yahoo Finance](https://finance.yahoo.com/technology/ai/articles/polish-ai-start-claims-first-080000634.html)

---
Canonical: https://techandbusiness.org/newswire/s5sUBgGYYDmkbqGWHbt-9k
Published: 2026-11-09T09:18:08.760Z
Story chronology: 2026-11-09T08:00:00.000Z
Retrieved: 2026-11-09T10:51:26.349Z
Publisher: Tech & Business (techandbusiness.org)