Nace AI Open-Sources Drex 1.5: A 9B Decision Model That Scores Options, Not Text
Quick Answer
Nace.AI has released Drex 1.5, a 9 billion parameter decision model that evaluates options in a single forward pass, achieving a Decision Index score of 58.08 on version 0.3.1.
Quick Take
The model can process up to 128,000 tokens, enhancing decision-making capabilities for various applications.
Key Points
- Drex 1.5 is a 9B parameter decision model from Nace.AI.
- It scores 58.08 on the Decision Index 0.3.1 benchmark.
- The model can handle up to 128,000 tokens in a single pass.
- Open-sourcing Drex 1.5 enables wider access for developers.
- The model focuses on scoring options rather than text.
Article Excerpt
From source RSS / original summaryNace. AI has open-sourced Drex 1. 5, a 9B decision model that returns a probability for every option in 1 forward pass. It scores 58. 08 on Decision Index 0. 3. 1 and reads up to 128K tokens. The post Nace AI Open-Sources Drex 1. 5: A 9B Decision Model That Scores Options, Not Text appeared first on MarkTechPost.
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from MarkTechPost
See more →Microsoft AI Releases Microsoft-Decision-1: A Qwen3.5-9B Decision-Scoring Model
Microsoft has launched Microsoft-Decision-1, a decision-scoring model derived from Alibaba's Qwen3.5-9B. This model focuses on routing, classification, verification, and agent control, providing calibrated probabilities for fixed answer options instead of generating text. It is now available in Microsoft Foundry and OpenRouter.