TSK-Bench · Build arena
Which AI model builds the best reading list app?
Every model got the same request, word for word, in Taskade Genesis. Here is how each one did, best first.
Last test · 3 builds
A simple reading list: books with a title, an author and a status (to read, reading or done), on one page that lists them and filters them by status.
What “works” means here
- The app opens and runs from the one request, with no fix from us.
- We use it the way a customer would: we fill in its form or log an entry, then check that every answer was saved.
- It covers what the request asked for. "Works, with gaps" means it runs but misses part of the request.
Ranked results
Works first, then works with gaps, then no app. Each result is one group, with its models listed by name.
| Model | |||
|---|---|---|---|
| Works · 3 | |||
Claude Sonnet 5 A book added from the app saved, and each status filter showed the right books. Works1 build · Tested | Works | 1 | |
Grok 4.7 Stat cards, an add form and status filters. A book added from the app saved, and each filter showed the right books. Works1 build · Tested | Works | 1 | |
Grok Build 0.1 Built the list and its filters, but its closing summary described the app in jargon in place of plain words. Works1 build · Tested | Works | 1 | |
Each row is one model version: its newest test on this request, the number of builds behind it, and what we found. Rows with the same result form one group and are listed by model name. A direction, not a final rank.
More Build arena tests
No side-by-side results published yet: Sales CRM, Inspection app, AI governance tracker, Habit tracker app, and Recipe app.
The Build arena →The full TSK-Bench ranking →Download the data (JSON)
How we grade these apps: read the full method.
FAQ
Which AI model builds the best reading list app?
In our tests, Claude Sonnet 5, Grok 4.7, and Grok Build 0.1 all built a working app. Each result comes from one to three builds, so read it as a direction, not a final rank.
How many AI models were tested on this reading list app request?
Models tested: 3, from 2 model families. Each got the same request, word for word. 3 worked.
Can I build a reading list app in Taskade?
Yes. Describe the reading list app in Taskade Genesis in your own words, pick a model or let TSK-1 Auto choose, and ask for changes after the first build.