# Apertus: Democratizing Open and Compliant LLMs for Global Language Environments

arXiv: https://arxiv.org/abs/2509.14233 · HTML: https://mlsanity.com/paper/2509.14233/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Sep 2025.

## Built on by (most cited first, 12 of 12)

- [Global PIQA: Evaluating Commonsense Reasoning Across 100+ Languages and Cultures](https://mlsanity.com/paper/2510.24081/) (2025)
- [K2-V2: A 360-Open, Reasoning-Enhanced LLM](https://mlsanity.com/paper/2512.06201/) (2025)
- [Marco-MoE: Open Multilingual Mixture-of-Expert Language Models with Efficient Upcycling](https://mlsanity.com/paper/2604.25578/) (2026)
- [Think Multilingual, Not Harder: A Data-Efficient Framework for Teaching Reasoning Models to Code-Switch](https://mlsanity.com/paper/2604.15490/) (2026)
- [M"OVE: A Holistic LLM Benchmark for the German Public Sector](https://mlsanity.com/paper/2606.13111/) (2026)
- [A Sovereign, Open-Source Foundation Model for German and English](https://mlsanity.com/paper/2607.09424/) (2026)
- [Optimizer Memory Schedules for Outscaling the Overtraining Axis](https://mlsanity.com/paper/2609.04577/) (2026)
- [Exploring Adversarial Robustness and Safety Alignment in Multilingual Multi-Modal Large Language Models](https://mlsanity.com/paper/2606.03793/) (2026)
- [sk-bench: A Native-First Benchmark for Evaluating Large Language Models in Slovak](https://mlsanity.com/paper/2610.09152/) (2026)
- [Wieszcz-XIX: A 3.1-Billion-Word Corpus of Pre-1918 Polish and Temporally Bounded Language Models Trained From Scratch](https://mlsanity.com/paper/2610.10592/) (2026)
- [Adapting English Quality Classifiers for Multilingual LLM Pretraining Data Selection](https://mlsanity.com/paper/2610.11585/) (2026)
- [Project Greenhouse: Progress Toward Fully Open and Sovereign Agentic Search](https://mlsanity.com/paper/2610.11922/) (2026)

## Abstract (arXiv)

We present Apertus, a fully open suite of large language models (LLMs) designed to address two systemic shortcomings in today's open model ecosystem: data compliance and multilingual representation. Unlike many prior models that release weights without reproducible data pipelines or regard for content-owner rights, Apertus models are pretrained exclusively on openly available data, retroactively respecting `robots.txt` exclusions and filtering for non-permissive, toxic, and personally identifiable content. To mitigate risks of memorization, we adopt the Goldfish objective during pretraining, strongly suppressing verbatim recall of data while retaining downstream task performance. The Apertus models also expand multilingual coverage, training on 15T tokens from over 1800 languages, with ~40% of pretraining data allocated to non-English content. Released at 8B and 70B scales, Apertus approaches state-of-the-art results among fully open models on multilingual benchmarks, rivalling or surpassing open-weight counterparts. Beyond model weights, we release all scientific artifacts from our development cycle with a permissive license, including data preparation scripts, checkpoints, evaluation suites, and training code, enabling transparent audit and extension.