Model vendor
Nous Research
Nous Research is an AI research organization focused on developing open-source large language models. Known for the Hermes and Capybara model series, they specialize in fine-tuning and instruction-following capabilities.
Updated Aug 10, 2026. Data as of 2026-08-07
Published models1
Published versions1
Open defaults0
CountryUS
Nous Research models
Default-version specifications and scored-version capability values are labeled separately.
| NR | Hermes 3 70B | 40.2 | 60.0% | 131.1K | Closed weights | Hermes 3 70B |
Nous Research capability scores
Each unique model uses its latest scored version.
Nous Research highlights
Leaders from this vendor's current published catalog.
Top scoreHermes 3 70B40.2 LLMBoardLargest contextHermes 3 70B131.1K tokens
Open-weight defaults0of 1 published models
What is Nous Research?
Vendor context from the published model registry.
Nous Research is an AI research organization focused on developing open-source large language models. Known for the Hermes and Capybara model series, they specialize in fine-tuning and instruction-following capabilities.
Model ownership is separate from API hosting. One model can be offered by multiple API providers with different prices.
- Vendor
- Nous Research
- Published models
- 1
- Published versions
- 1
- Country
- US
- Founded
- Not published
Vendor description and inventory come from the published model registry.
FAQ
Common questions about Nous Research.
What is Nous Research's highest-ranked model?
Hermes 3 70B currently has the strongest published LLMBoard score from this vendor.
How many Nous Research models are tracked?
The current public catalog contains 1 independently selectable Nous Research model products and 1 published versions.
Does Nous Research host every listed model API?
Not necessarily. Vendor identifies the model developer; API providers are tracked separately.
Does Nous Research publish open-weight models?
No current default version is marked as open weight.