# René-1: A 31B Decision Reader That Knows When It Is Sure

> An open-weights 31B model that reads a document and returns a calibrated probability for every option of every question, in one pass.

- **Authors:** Elon Salfati
- **Published:** September 27, 2026
- **Canonical URL:** https://elonsalfati.com/research/rene-1
- **Tags:** decision-models, calibration, open-weights
- **Type:** Model
- **Venue:** Hugging Face
- **Status:** published
- **Website:** https://huggingface.co/salfatigroup/rene-1-31b-fp8

## Abstract

René-1 is a decision model. You send a document and a set of typed questions: pick one option, answer yes or no, or place the document on a scale. It reads the document and every question in one pass, each question on its own, and answers each with a probability for every option you declared. There is no generated text to parse. The weights are stored in FP8, so the whole model runs on one GPU.

## Key takeaways

- It answers typed questions about a document (yes or no, one of several options, or a point on a scale) with a probability for every option, and generates no text.
- It is a full fine-tune of a 31B open-weights model: one epoch on 396,500 rows from 56 task families, trained with a log-score loss to put probability on the right option.
- The model card reports 64.18 balanced skill on 37 of the 40 Decision Index 0.2 benchmarks, against 54.75 for the next model, and a median calibration error of 0.046. These figures are self-reported.
- Stored in FP8, it serves on one GPU: 92.1 ms at the median for five questions over 641 input tokens on one NVIDIA B200.
- The weights are open under Apache 2.0.

## Cite

```bibtex
@misc{salfati2026ren1,
  title = {{René-1: A 31B Decision Reader That Knows When It Is Sure}},
  author = {Elon Salfati},
  year = {2026},
  howpublished = {Hugging Face},
  url = {https://elonsalfati.com/research/rene-1}
}
```

---
Source: https://elonsalfati.com/research/rene-1