# MaxxBench tests coding models on modified DeepSWE tasks

> Original title: The only model that actually scored higher on DeepSWE when small changes were made to the task, was Opus 5.5

- Source: Deedy
- Published: 2026-11-07T16:44:30.000Z
- Bad Influence: https://badinfluence.news/items/conhvy2joo1oluxtgcdd4254v
- Original: https://x.com/deedydas/status/2119108746362474976

## Summary

Deedy says Opus 5.5 was the only model whose DeepSWE score rose when small task changes were made, calling most models severely benchmaxxed. loresjpg introduces MaxxBench, 89 DeepSWE tasks with slight changes to instructions or starting code, reporting that models clustered around 74% on DeepSWE end up 23 percentage points apart.

## Post

The only model that actually scored higher on DeepSWE when small changes were made to the task, was Opus 5.5

Most models are severely benchmaxxed.

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHWiWLMfb0AAob62.jpg&mode=thumb&exp=1794268800&sig=97de90e5e1239888)

## Quoted post @loresjpg

> Nice DeepSWE score! Does it survive a lowercase filename?
> 
> Introducing MaxxBench: 89 DeepSWE tasks with small changes to the instructions or starting code. Same engineering problem, slightly different requirement.
> 
> Models clustered around 74% on DeepSWE end up 23 pp apart.
> 
> Good at coding, or good at DeepSWE? 🧵

https://x.com/loresjpg/status/2118880329490637049