HackerPapers

arXiv:2508.18255cs.AI

Hermes 4 Technical Report

Ryan Teknium, Roger Jin, Jai Suphavadeeprasit, Dakota Mahan, Jeffrey Quesnelle, Joe Li, Chen Guang, Shannon Sands, Karan Malhotra

Abstract

We present Hermes 4, a family of hybrid reasoning models that combine structured, multi-turn reasoning with broad instruction-following ability. We describe the challenges encountered during data curation, synthesis, training, and evaluation, and outline the solutions employed to address these challenges at scale. We comprehensively evaluate across mathematical reasoning, coding, knowledge, comprehension, and alignment benchmarks, and we report both quantitative performance and qualitative behavioral analysis. To support open research, all model weights are published publicly at https://huggingface.co/collections/NousResearch/hermes-4-collection-68a731bfd452e20816725728

arXiv comments
Journal reference
DOI
Subjects
cs.AIArtificial Intelligence

On Hacker News

Linked by 2 identifiable commenters in 2 comments across 2 threads, from Aug 2025 to Aug 2025. Found in 1 HN submission from Aug 2025 to Aug 2025. Open submission discussions.

Comments linking this paper, per year.

Discussed in comments2 threads

  1. Hermes 4 1 comment
    • Technical Report: https://arxiv.org/abs/2508.18255 Download Models: https://huggingface.co/collections/NousResearch/hermes-4-col...

      bekleinView on HNParent context

Submitted to Hacker News

  • Hermes 4

    Technical report: https://arxiv.org/pdf/2508.18255

Connected through shared HN threads, not inferred similarity or a recommendation.