# ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks

arXiv: https://arxiv.org/abs/2605.25388 · HTML: https://mlsanity.com/paper/2605.25388/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 65 references that are in the map.
- First posted on arXiv 25 May 2026.

## Builds on (most cited first, 6 of 6)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [PEER: A Comprehensive and Multi-Task Benchmark for Protein Sequence Understanding](https://mlsanity.com/paper/2206.02096/) (2022)
- [RiNALMo: General-Purpose RNA Language Models Can Generalize Well on Structure Prediction Tasks](https://mlsanity.com/paper/2403.00043/) (2024)
- [BEND: Benchmarking DNA Language Models on biologically meaningful tasks](https://mlsanity.com/paper/2311.12570/) (2023)
- [SpanSeq: Similarity-based sequence data splitting method for improved development and assessment of deep learning projects](https://mlsanity.com/paper/2402.14482/) (2024)
- [NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction](https://mlsanity.com/paper/2511.02888/) (2025)

## Abstract (arXiv)

Nucleotide sequences constitute the fundamental genetic basis of biological systems, rendering viral genomic analysis critical for biomedical advancement. Despite progress in biological foundation models, specifically nucleotide foundation models (NFMs), the field lacks a unified standard for viral genomics to facilitate community development and enforce biosecurity constraints. To address this, we introduce ViroBench, the first comprehensive and large-scale benchmark specifically designed for NFMs in viral settings. ViroBench evaluates models across two critical dimensions: biological understanding and latent biosecurity risk, covering 18 diverse scenarios within 4 task types. Extensive evaluation of 66 NFMs across diverse architectures yields three critical conclusions. Firstly, NFMs exhibit a performance degradation in biological understanding under phylogenetic and temporal shifts, indicating weak extrapolation capabilities. Secondly, generation tasks reveal a decoupling between statistical likelihood and biological functional validity, posing latent biosecurity risks. Thirdly, controlled ablation studies reveal that taxonomic diversity in pretraining data outweighs parameter scale. Specifically, a lightweight baseline trained on diverse data achieves a 67.5% performance gain over its original model. Overall, ViroBench provides interpretable, diagnostic evaluations and a reproducible measurement framework for future research on viral nucleotide foundation models. The datasets and code are publicly available at https://github.com/QIANJINYDX/ViroBench.