Nous Research, open weights

# Hermes 4 405B

> Hermes 4 405B by Nous Research. 2 published benchmark results. API: $1 in / $3 out per M tokens. 131K context. Scores, sources and comparisons.
- Canonical page: https://noometry.com/models/hermes-4-405b
- Last updated: 2026-10-10
- Title: Hermes 4 405B Benchmarks, Price & Rank (October 2026)

Hermes 4 405B by Nous Research has 2 published benchmark results on Noometry, not yet enough to be ranked. API pricing starts at $1 per million input tokens and $3 per million output tokens, with a 131K-token context window.

Last verified October 10, 2026

## Specifications

- **Noometry rank:** Unranked
- **Index score:** Not ranked
- **Evidence:** Sparse 2 results
- **Provider:** [Nous Research](https://noometry.com/providers/nous-research)
- **Released:** Unknown
- **Weights:** Open weights
- **Reasoning:** Yes
- **Context window:** 131K
- **Max output:** 118K
- **Input price:** $1 / M
- **Output price:** $3 / M
- **Blended price:** $1.50 / M
- **Output speed:** 23 tokens/s [Kagi](https://help.kagi.com/kagi/ai/llm-benchmark.html)
- **Value:** Not ranked
- **Knowledge cutoff:** Unknown
- **Input:** text
- **Hugging Face:** [NousResearch/Hermes-4-405B](https://huggingface.co/NousResearch/Hermes-4-405B)

## Category scores

Each category score combines every public result we have in that category.

Hermes 4 405B category scores

1.  Reasoning 26.1
2.  Writing & Preference 52.9
3.  0204060

Hermes 4 405B category ranks
| Category | Score | Rank | Results |
| --- | --- | --- | --- |
| [Reasoning](https://noometry.com/best/reasoning) | 26.1 | — | 1 |
| [Writing & Preference](https://noometry.com/best/writing) | 52.9 | — | 1 |

Sponsored placements are available on pages like this one. [Advertise on Noometry](https://noometry.com/advertise)

## Benchmark results

Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.

### Reasoning

Hermes 4 405B Reasoning benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [Kagi LLM Benchmark](https://noometry.com/benchmarks/kagi-reasoning) | 55.8% | #50 of 99, top 51% |  | [Kagi LLM Benchmark](https://help.kagi.com/kagi/ai/llm-benchmark.html) |  |
| [Kagi LLM Benchmark](https://noometry.com/benchmarks/kagi-reasoning) | 30.1% |  |  | [Kagi LLM Benchmark](https://help.kagi.com/kagi/ai/llm-benchmark.html) |  |

### Writing & Preference

Hermes 4 405B Writing & Preference benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [EQ-Bench Creative Writing](https://noometry.com/benchmarks/eqbench-creative-writing) | 1421 | #66 of 115, top 58% |  | [EQ-Bench](https://eqbench.com/creative_writing.html) |  |

## API pricing by provider

Hermes 4 405B API prices
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
| --- | --- | --- | --- | --- |
| [openrouter](https://openrouter.ai/nousresearch/hermes-4-405b) | $1 | $3 | — | 2026-10-10 |

[All Nous Research API prices →](https://noometry.com/llm-pricing/nous-research) [Estimate your cost →](https://noometry.com/tools/cost-calculator)

## Compare Hermes 4 405B

-   [Hermes 4 405B vs GPT-6 Astra](https://noometry.com/compare/gpt-6-astra-vs-hermes-4-405b)
-   [Hermes 4 405B vs Claude Fable 5.1](https://noometry.com/compare/claude-fable-5-1-vs-hermes-4-405b)
-   [Hermes 4 405B vs Claude Opus 5.5](https://noometry.com/compare/claude-opus-5-5-vs-hermes-4-405b)
-   [Hermes 4 405B vs Claude Opus 5](https://noometry.com/compare/claude-opus-5-vs-hermes-4-405b)
-   [Hermes 4 405B vs Claude Fable 5](https://noometry.com/compare/claude-fable-5-vs-hermes-4-405b)
-   [Hermes 4 405B vs GPT-6.1 Sol](https://noometry.com/compare/gpt-6-1-sol-vs-hermes-4-405b)
-   [Hermes 4 405B vs Gemini 3.8 Flash](https://noometry.com/compare/gemini-3-8-flash-vs-hermes-4-405b)
-   [Hermes 4 405B vs Kimi K3](https://noometry.com/compare/hermes-4-405b-vs-kimi-k3)
-   [Hermes 4 405B vs Grok 4.6](https://noometry.com/compare/grok-4-6-vs-hermes-4-405b)
-   [Hermes 4 405B vs Qwen3.8 Max](https://noometry.com/compare/hermes-4-405b-vs-qwen3-8-max)
-   [Hermes 4 405B vs GLM-5.3](https://noometry.com/compare/glm-5-3-vs-hermes-4-405b)
-   [Hermes 4 405B vs Muse Spark 1.3](https://noometry.com/compare/hermes-4-405b-vs-muse-spark-1-3)
-   [Hermes 4 405B vs DeepSeek V4 Pro](https://noometry.com/compare/deepseek-v4-pro-vs-hermes-4-405b)
-   [Hermes 4 405B vs MiMo-V2.6-Pro](https://noometry.com/compare/hermes-4-405b-vs-mimo-v2-6-pro)

## Other Nous Research models

-   [Hermes 3 405B Instruct](https://noometry.com/models/hermes-3-405b-instruct)
-   [Hermes 3 70B Instruct](https://noometry.com/models/hermes-3-70b-instruct)

## Frequently asked questions

### How good is Hermes 4 405B?

Hermes 4 405B by Nous Research has 2 published benchmark results on Noometry, not yet enough to be ranked. API pricing starts at $1 per million input tokens and $3 per million output tokens, with a 131K-token context window.

### How much does Hermes 4 405B cost?

Hermes 4 405B costs $1 per million input tokens and $3 per million output tokens on openrouter.

### What is Hermes 4 405B's context window?

Hermes 4 405B accepts up to 131K tokens of input and can write up to 118K tokens in one response.

### Is Hermes 4 405B open source?

Yes. Hermes 4 405B's weights are downloadable from Hugging Face (NousResearch/Hermes-4-405B); check the license for commercial terms.

### How fast is Hermes 4 405B?

Hermes 4 405B generated about 23 output tokens per second in the Kagi LLM Benchmark's timed runs. Speed varies by provider, load and reasoning effort.

### Cite this page

Noometry. (2026). Hermes 4 405B benchmarks and pricing. Retrieved October 10, 2026, from https://noometry.com/models/hermes-4-405b

Quote Noometry with a link back to this page. It is also available in [Markdown](https://noometry.com/md/models/hermes-4-405b.md).