# Solvent preprint reports 61.86% score across molecular synthesis planning benchmarks

_Published Monday, October 26, 2026 at 6:40 AM EDT · AI, Science · Latest · Tier 2 — Notable_

Researchers report that Solvent, an eight-billion-parameter language model, scored 61.86% across four benchmarks for planning how to make molecules from purchasable building blocks. The preprint reports a 2.1-fold performance improvement from reinforcement learning and results exceeding prior search-based systems and mid-scale language models.

The model learns through two rounds of post-training to alternate between planning reaction sequences, checking building-block availability and revising routes. The reported achievement concerns synthesis planning benchmarks, rather than demonstrated production of the target molecules.

## Sources

- [cs.AI updates on arXiv.org](https://arxiv.org/abs/2610.32308)

---
Canonical: https://techandbusiness.org/newswire/c4U3SS0MUlnd3Kexpxatct
Published: 2026-10-26T10:40:29.866Z
Story chronology: 2026-10-26T04:00:00.000Z
Retrieved: 2026-10-26T12:40:19.254Z
Publisher: Tech & Business (techandbusiness.org)