Qwen3.8 27B is an open-weight dense vision-language model from Qwen.
Hermes 4 405B
Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research.
SharkScore
#447 in Models
Why it scores 22.9
Hermes 4 405B has a SharkScore of 22.9/100, ranked #447 of 608 in Models (updated 2026-11-19).
Each part compares Hermes 4 405B with other listings in Models. Evidence covers 87% of the score's weight.
- Adoption
- 0 · 30%
- User reviews
- no data · 25%
- Maintenance
- 1 · 20%
- Trust & transparency
- 80 · 15%
- Momentum
- no data · 10%
Paying never changes this score. How ranking works · method v2026-11-18.2
RankShark review of Hermes 4 405B
Automated evaluation by RankShark · 18 Nov 2026 · method v1.0 · How we review
We were not paid for this review.
As of 2026-11-18, Hermes 4 405B is a text reasoning model with a 131,072-token context window and OpenRouter-listed rates of $1 per million input tokens and $3 per million output tokens. [E1, E2, MEASURED]
Hermes 4 405B is a Nous Research model based on Llama 3.1 405B. The vendor describes it as a hybrid-reasoning model with tool use and structured-output support. [E1]
Best for
- Teams looking for a model with optional hybrid reasoning. · model card
- Developers who need tool calls or schema-based structured output. · model card
Not for
- Workloads that require image or audio input or output; the OpenRouter listing identifies text as the model's input and output modality. · OpenRouter
Key features
- Hybrid reasoning. The vendor says the model can use explicit <think> segments when it chooses to deliberate, and reasoning can be enabled through the chat template. · model card
- Tool use. The vendor says tool calls can be interleaved with reasoning and provides a tagged format for tool calls. · model card
- Structured output. The vendor says the model was trained to produce valid JSON for given schemas and repair malformed objects. · model card
- Context window. The OpenRouter listing reports a 131,072-token context window. · OpenRouter
Pros
- The vendor describes both hybrid reasoning and a way to enable it through the chat template. · model card
- The vendor documents tool calls and structured-output support. · model card
- The Hugging Face page lists inference options including Nous Portal, Chutes, Nebius, and Luminal. · model card
Cons
- The OpenRouter listing specifies text input and text output, not image or audio modalities. · OpenRouter
- The vendor suggests tensor-parallel inference engines for production serving on multi-GPU nodes. · model card
- No free plan or free trial stated on the pages we checked.
- Whether customer data is used for model training is not stated on the pages we checked.
Pricing
| Plan | Price | Limits |
|---|---|---|
| OpenRouter model listing | $1 per million input tokens; $3 per million output tokens | 131,072-token context window. |
Checked 18 Nov 2026
- Free plan
- Not stated (checked 18 Nov 2026)
- Free trial
- Not stated (checked 18 Nov 2026)
- Trains on customer data
- Not stated (checked 18 Nov 2026)
- Data retention
- Not stated (checked 18 Nov 2026)
- Data regions
- Not stated (checked 18 Nov 2026)
- Data processing agreement
- Not stated (checked 18 Nov 2026)
- AI models used
- Not stated (checked 18 Nov 2026)
- API
- The OpenRouter listing includes chat completions, completions, messages, and responses endpoints. · OpenRouter
- SDKs
- Not stated (checked 18 Nov 2026)
- Webhooks
- Not stated (checked 18 Nov 2026)
- Platforms
- The vendor lists Nous Portal, Chutes, Nebius, and Luminal as inference providers. OpenRouter lists the model and its API endpoints. · model card, OpenRouter
- Security claims
- No security certification stated (checked 18 Nov 2026)
What we measured
- Context window (OpenRouter listing) · now
- 131,072 tokens
- Price per million tokens (OpenRouter listing) · now
- $1 in, $3 out
- Package downloads · 30 days
- 3,381
How we tested · sources
- Hourly uptime and response-time checks of the product's URL.
- Repository, release and download data from GitHub, npm, PyPI and Hugging Face where they exist.
- We did not sign up, pay, or use the product as a customer.
- model card: https://huggingface.co/NousResearch/Hermes-4-405B · fetched 18 Nov 2026
- OpenRouter: https://openrouter.ai/nousresearch/hermes-4-405b · fetched 18 Nov 2026
- 18 Nov 2026: Plans or prices changed on the pricing page.
Something wrong? Report an error with a public link that shows it; corrections re-run the review.
Top alternatives to Hermes 4 405B
See all- 67.1ModelOpen source
- 65.5
Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per t
ModelOpen source - 64.7
Qwen3.8 Flash is a multimodal reasoning model from Alibaba.
ModelOpen source - 64.3
Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026.
ModelOpen source