# Nace AI releases Drex, four open decision models for probability-based choices

> Original title: Banger report on foundation decision models.

- Source: Elvis Saravia
- Published: 2026-11-06T13:16:02.000Z
- Bad Influence: https://badinfluence.news/items/b0zpvghsemlal0igz7ifwkj80
- Original: https://x.com/omarsar0/status/2118693892300439722

## Summary

Nace AI presents Drex, a family of four open decision models at 8B, 9B, 35B with 3B active, and 27B parameters. The 27B Max model scores 67.52 on the public Decision Index 0.4.1 suite versus 60.70 for Jev 1.14.0, and answers in 183 ms versus 3.5 s for Claude Opus 5.5. Training adds reinforcement learning from adjusted feedback, which cuts the rate of flipped answers under option reordering from 6.3% to 4.2%.

## Post

Banger report on foundation decision models.

This work presents a 27B open decision model that lands within 1.6 points of Claude Opus 5.5 on Decision Bench v4 and answers in 183 ms instead of 3.5s.

Nace AI released Drex, a family of four open decision models at 8B, 9B, 35B with 3B active, and 27B.

You give the model a state, such as a document, a record, or an agent's context, plus questions with a fixed set of options. It returns a probability for each option without generating text.

The 27B Max model scores 67.52 on the public Decision Index 0.4.1 suite, against 60.70 for Jev 1.14.0.

On Decision Bench v4, it is statistically tied with GPT-6 Sol and d3-turbo. It also has the best accuracy among decision models on DecideBench.

Model Training:

After fine-tuning, training adds reinforcement learning from adjusted feedback (RLAF). A teacher model proposes a probability for each option, and the verified answer adjusts it, so the model trains on calibrated targets in place of one-hot labels. RLAF adds 2.0 Decision Index points, and a consistency loss lowers the rate of flipped answers when the options are reordered from 6.3% to 4.2%.

HF: https://huggingface.co/nace-ai/drex-max-v1

Paper: https://arxiv.org/abs/2611.07854

Chat with Paper: https://academy.dair.ai/papers/towards-foundation-decision-models-drex-2611.07854

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHWcc3gqbYAAOdH5.jpg&mode=thumb&exp=1794182400&sig=65cace5870b98c54)