Skip to content

Nous Research · Chat

Hermes 4 405B

Nous Research 🇺🇸ChatOpen weights. One of its sources says the weights are publicly available.
From Cortecs AI's listing:
Hermes 4 405B is a frontier hybrid-mode reasoning model built on Llama 3.1, optimized for advanced logic, math, coding, and structured output generation.
llminfo IQ
118.8
Market median price
$1.50 blended / 1M
Max context
131K
Listings
11

Evidence and sources

🤗 NousResearch/Hermes-4-405Bllminfo IQ 118.8, ranked among chat models. From 7 benchmarks. A fair amount of data behind it.How llminfo IQ is computedPoor value (38.3). Costs more per task than its benchmark results predict. From 2 benchmarks with measured task costs. Little data behind it, so treat it as a rough estimate.How Value for money worksReleased 26 Aug 2025 Training-data cutoff, as its sources state it Maker HQ: US (source)
All rankings: #318 on OpenRouter today #344 on OpenRouter this week #364 on OpenRouter this monthSources: GenAI Prices data, Models.dev data, AI/ML API data, OpenRouter data docs, Cortecs EU Router data, llminfo researchPrimary data from GenAI Prices from Models.dev: name, weights availability from AI/ML API: primary mode from OpenRouter: knowledge cutoff from Cortecs EU Router: description from llminfo research: release date
Tags from its sources:instructtools

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ
We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 04:34 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 7 maker's prices; 1 official partner's price; 2 market median prices.

Input & output

as stated by the model's providers
Text
Text

Capabilities

Supported operations and provider-stated features

ReasoningFunction callingStructured outputPrompt caching

Listings

 Cortecs AIhermes-4-405bSources: Cortecs EU Router data, Models.dev data128K——
 Flowdotnousresearch/hermes-4-405bSource: FlowDot data131K$1.00$3.00——
 Hugging FaceInference by Nebius AI StudioNousResearch/Hermes-4-405BSources: GenAI Prices data, Hugging Face Inference Providers data131K$1.00$3.00——
 Kilonousresearch/hermes-4-405bSources: Kilo AI Gateway data, Models.dev data131K$1.00cache read $0.20$3.00——
 OpenRouterInference by Nebius AI Studionousresearch/hermes-4-405b · fp8Source: OpenRouter data docs131K$1.00cache read $0.20$3.0038332ms
 OpenRouternousresearch/hermes-4-405bSources: GenAI Prices data, Models.dev data, OpenRouter data docs131K$1.00cache read $0.20$3.00——
 RequestyInference by Nebius AI Studionebius/nousresearch/hermes-4-405bSource: Requesty data128K$1.00$3.00——
 Nebius AI Studionebius/NousResearch/Hermes-4-405BSources: LiteLLM data, Models.dev data131K$1.00cache read $0.20$3.00——

3 listings without a price are hidden.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Coding

Reasoning

Vision

Other

Data credits: EQ-Bench (Samuel J. Paech) — cite paech2023eqbench · SnakeBench (Greg Kamradt / ARC Prize Foundation), MIT (licence)

Also known as: nebius/nousresearch/hermes-4-405b, nousresearch/hermes-4-405b

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works