---
title: "Fidelity's Text2Model Turns Plain English Into Solver Code but Struggles at 38%"
subtitle: "A new benchmark and copilot suite tests whether LLMs can turn plain-English problem descriptions into working optimization models, with mixed results."
url: "https://alphasignal.ai/news/fidelity-s-text2model-turns-plain-english-into-solver-code-but-struggles-at-38"
author: "AlphaSignal Newsroom"
author_url: "https://alphasignal.ai/editorial-team"
company: "AlphaSignal"
company_url: "https://alphasignal.ai/company/alphasignal"
published: "2026-04-14T00:00:00.000Z"
updated: "2026-08-23T23:28:13.496Z"
type: "Paper"
topics:
  - "Development"
  - "Llms"
subtopics:
  - "Code Generation"
  - "Structured Output"
upvotes: 2607
source_url: "https://arxiv.org/abs/2604.12955"
comments: 0
truncated: true
---

# Fidelity's Text2Model Turns Plain English Into Solver Code but Struggles at 38%

> A new benchmark and copilot suite tests whether LLMs can turn plain-English problem descriptions into working optimization models, with mixed results.

Turning a business problem written in plain English into a working constraint model has always been a job for specialists. A new research effort called [Text2Model](https://skadio.github.io/text2model/) and its accompanying [Text2Zinc](https://huggingface.co/datasets/skadio/text2zinc) dataset put large language models to the test on exactly that task, and the results suggest we are not quite at the push-button stage yet.

The work comes from researchers at Fidelity Investments' AI Center of Excellence and Brown University. They formalized the text-to-model translation problem, proposed several Text2Model copilots with an online leaderboard, and contributed the Text2Zinc dataset to enable benchmarking across both optimization and satisfaction problems in a solver-agnostic manner. Everything, including an interactive editor with a built-in AI assistant, is open source.

## The modeling bottleneck nobody wants to talk about

Optimization solvers have gotten dramatically faster over the past few decades, but the workflow around them has barely changed. Someone with deep expertise still has to translate a messy real-world problem into a formal specification of variables, domains, and constraints before a solver can touch it. Domain experts who understand their problem often lack the specialized knowledge required for formal modeling, and the resulting dependency on modelers creates operational bottlenecks and can introduce misinterpretation of domain-specific requirements during translation.

_Preview only. Full text requires an AlphaSignal Pro account._

## Sources

- [Text2Model: Modeling Copilots for Text-to-Model Translation](https://arxiv.org/html/2604.12955)
- [Text2Zinc dataset on HuggingFace](https://huggingface.co/datasets/skadio/text2zinc)
- [Text2Model project page](https://skadio.github.io/text2model/)
- [MiniZinc](https://www.minizinc.org/)
- [Gala: Global LLM Agents for Text-to-Model Translation](https://arxiv.org/abs/2509.08970)