Year: 2025
Type: preprint
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
Source: arXiv (Cornell University)
Authors: Teknium, Ryan, Jin, Roger, Suphavadeeprasit, Jai, Mahan, Dakota, Quesnelle, Jeffrey, Li, Joe, Guang, Chen, Sands, Shannon, Malhotra, Karan
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7077853256
Cites:
Cited by:
Related to: