# Preprint finds smaller LLM groups can cut prediction costs

_Thursday, August 27, 2026 at 12:00 AM EDT · AI, Science · Latest · Tier 2 — Notable_

A preprint describes a method for selecting a smaller group of language models for future-prediction tasks by clustering models according to reasoning traces from independent development tasks. The authors evaluated 25 models on seven development benchmarks and two prediction benchmarks. They report that a three-model medoid group outperformed conventional voting over all 25 models on both prediction benchmarks, while using 88% fewer model calls and about 80% less inference cost.

## Sources

- [cs.AI updates on arXiv.org](https://arxiv.org/abs/2608.24001)

---
Canonical: https://techandbusiness.org/newswire/RdQ9_USJkITh7NjTu_u4UK
Retrieved: 2026-08-27T08:47:20.578Z
Publisher: Tech & Business (techandbusiness.org)