Hermes 4 – Llama-3.1 405B (Non-reasoning)
Analysis Summary
Hermes 4 built on Llama-3.1 405B (Non-reasoning) is Nous Research's large-scale fine-tune of Meta's flagship open-weight base, targeting general instruction following and content generation. Its MMLU-Pro score of 0.729 and GPQA of 0.536 place it in a capable mid-tier bracket, and its LiveCodeBench score of 0.546 shows meaningful coding ability for a non-reasoning variant.
For businesses, this model suits content generation, summarisation, and structured writing tasks where a large, well-tuned model is needed but extended chain-of-thought reasoning is not. Its agentic index is limited, so it is not well suited to multi-step tool-use workflows. At $1 input and $3 output per million tokens, it sits at a moderate price point for a 405B-class model.
Teams needing a capable, large non-reasoning model for content pipelines will find it a workable option, though the reasoning variant of the same family offers substantially stronger performance on harder tasks.
Assessed June 6, 2026
Editorial notes
Hermes 4 Llama-3.1 405B (Non-reasoning) from Nous Research delivers strong MMLU-Pro and GPQA scores with competitive coding capability, priced at $1/$3 per million tokens.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How Hermes 4 – Llama-3.1 405B (Non-reasoning) compares
Hermes 4 – Llama-3.1 405B (Non-reasoning) ranks #199 of 378 AI models we track for overall intelligence, #157 of 315 for coding, #192 of 289 for agentic tasks. At $1.00 per million input tokens it is cheaper than 25% of comparable models.
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does Hermes 4 – Llama-3.1 405B (Non-reasoning) stack up?
Compare side-by-side with other professional models.
Model Information
| Provider | Nous Research |
| Release Date | August 27, 2025 |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $1.00 | $0.001000 |
| Output | $3.00 | $0.003000 |
Leaderboard Categories
Frequently asked questions about Hermes 4 – Llama-3.1 405B (Non-reasoning)
How much does Hermes 4 – Llama-3.1 405B (Non-reasoning) cost?
Hermes 4 – Llama-3.1 405B (Non-reasoning) costs $1.00 per million input tokens and $3.00 per million output tokens.
Is Hermes 4 – Llama-3.1 405B (Non-reasoning) good for coding?
On our coding benchmark index, Hermes 4 – Llama-3.1 405B (Non-reasoning) ranks #157 of 315 models, placing it in the broader range of the field for code generation and debugging.
Who created Hermes 4 – Llama-3.1 405B (Non-reasoning)?
Hermes 4 – Llama-3.1 405B (Non-reasoning) is developed by Nous Research and was released on August 27, 2025.
