# Clearly defined tasks can guide which model size to choose

> Original title: how clearly a task is defined can help guide model choice

- Source: Together AI
- Published: 2026-11-04T17:06:38.000Z
- Bad Influence: https://badinfluence.news/items/jr5hajzkmko4udfzfson3ntb1
- Original: https://x.com/togethercompute/status/2118027151714689334

## Summary

Together AI says scoped work such as writing tests or renaming an API may not need the largest model. Open-ended work like a framework upgrade or auth refactor is where a larger model's reasoning is more likely to pay off.

## Post

how clearly a task is defined can help guide model choice

scoped work like writing tests or renaming an API may not need your largest model

open-ended work like a framework upgrade or an auth refactor is where a larger model's reasoning is more likely to pay off

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHWS-eDMX0AApIAH.jpg&mode=thumb&exp=1794009600&sig=820e9aa35309e1eb)