Hermes 4 Technical Report
Teknium, Ryan, Jin, Roger, Suphavadeeprasit, Jai, Mahan, Dakota, Quesnelle, Jeffrey, Li, Joe, Guang, Chen, Sands, Shannon, Malhotra, Karan
–arXiv.org Artificial Intelligence
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.org Artificial Intelligence
Sep-3-2025
- Country:
- North America > United States (1.00)
- Asia > China (1.00)
- Genre:
- Instructional Material (0.67)
- Research Report (0.64)
- Industry:
- Law Enforcement & Public Safety > Crime Prevention & Enforcement (1.00)
- Health & Medicine > Therapeutic Area (1.00)
- Education (0.93)
- Banking & Finance (0.92)
- Information Technology (0.67)
- Media (0.67)
- Law
- Civil Rights & Constitutional Law (1.00)
- International Law (0.92)
- Government
- Technology: