ZMIME
Nous Research · Released Nov 6, 2026

Arete-27B

Fine-tuned from Qwen3.8-27B using about 52.8 million tokens for research on value alignment.

  • New
  • Open weights
Capability
—No ECI score yet
Input
—No listed price
Output
—No listed price
Context
—tokens
Pricing

What it costs

No per-token price is published for this model yet.

No per-token price is listed for this model on models.dev.

Capability

Independent benchmarks

Epoch AI has not published a Capabilities Index score for Arete-27B yet.

Specifications

The details

Lab
Nous Research
Task
Language generation and alignment
Published capabilities
Fine-tuned from Qwen3.8-27B using about 52.8 million tokens for research on value alignment.
Model size
27B parameters
Access
Public weights, evaluation and training dataset
Released
Nov 6, 2026
Context window
— tokens
Inputs
Text
Output
Text
Reasoning
Unconfirmed
Tool calling
Unconfirmed
Structured output
Unconfirmed
Weights
Open weights

Nous Research model documentation

Same lab

More from Nous Research

Questions

About Arete-27B

How much does Arete-27B cost?

Arete-27B has no published per-token API price on models.dev yet.

How good is Arete-27B?

Epoch AI has not published a Capabilities Index score for Arete-27B yet.

Is Arete-27B open source?

Yes. Nous Research publishes the weights, so it can be downloaded and self-hosted.

What inputs does Arete-27B support?

Arete-27B accepts text. Fine-tuned from Qwen3.8-27B using about 52.8 million tokens for research on value alignment.

When was Arete-27B released?

Nous Research released Arete-27B on Nov 6, 2026.

What are the best alternatives to Arete-27B?

The closest current models from other labs on capability, price and release date are GPT-6 Cyber (OpenAI), ERNIE 5.5 Flash Base (Baidu), Inkling 2 Small (Thinking Machines, $0.30 / $1.00) and Ling 3.2 Flash (inclusionAI).