---
format: "aidr-story-markdown/v1"
id: "bd3c7ebfc9f888c4317c804043effab201b8ba2c0555abcef776fbbe573cc815"
canonical_url: "https://aidr.today/bd3c7ebf?lang=en"
title: "DishwasherBench – Can Frontier Models Stack a Dishwasher?"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-13T08:24:06.000Z"
category: "Open Source"
topics: ["llm","open-source"]
source_urls: ["https://github.com/composo-ai/DishwasherBench","https://news.ycombinator.com/item?id=50068437"]
summary: "DishwasherBench is a browser-playable dishwasher-loading game built on a physical simulation to benchmark language models."
---

# DishwasherBench – Can Frontier Models Stack a Dishwasher?

> [Open the canonical story](<https://aidr.today/bd3c7ebf?lang=en>)

**Published:** 2026-10-13T08:24:06.000Z
**Category:** Open Source
**Topics:** llm, open\-source

## Summary

DishwasherBench is a browser\-playable dishwasher\-loading game built on a physical simulation to benchmark language models\.

## Sources

- [Story source](<https://github.com/composo-ai/DishwasherBench>)
- [Discussion](<https://news.ycombinator.com/item?id=50068437>)