TSK-Bench · Code arena

Which AI model codes the change you ask for, without breaking the app?

After the first build, we send one follow-up coding request in the same chat. The change must land without breaking what already worked. Each page ranks one kind of change.

Each result covers the first build and the follow-up change together. Where the test recorded it, the finding says what happened to the change.

Last test Oct 8, 2026 · 23 models · 55 builds

Results by change

Open a kind of change to see every model ranked on it, with the app it was made to and the request word for word.

Code results by change
Change	Models	Works	Newest test
Add a page to an app you built Add a new page to an app the model already built. The new page must work, and every page that worked before must still work. Made to: game tracker app.	14	9	Oct 8, 2026
Add a field to a form Add one more question to a form the model already built. The new answer must save, and every earlier answer must still save. Made to: intake form.	23	12	Oct 8, 2026

No same-request table yet: Change text and headings.

Every model across these changes

How many tested changes each model version got working. Each result comes from one to three builds, so read it as a direction.

Models across Code changes
Model	Works on
Claude Sonnet 5 Anthropic · Own key	2 of 2 changes
DeepSeek V4 Pro DeepSeek · Available	2 of 2 changes
DeepSeek V4 Pro 0813 DeepSeek · Not in Taskade	2 of 2 changes
DeepSeek V4 Pro, max thinking DeepSeek · Available	2 of 2 changes
GPT-5.6 Sol OpenAI · Available	2 of 2 changes
Grok 4.5 xAI · Retired	2 of 2 changes
Grok 4.7 xAI · Available	2 of 2 changes
DeepSeek V4 Pro, high thinking DeepSeek · Available	1 of 2 changes
DeepSeek V4.1 Flash DeepSeek · Available	1 of 2 changes
GPT-5.6 Luna OpenAI · Available	1 of 2 changes
GPT-5.6 Terra OpenAI · Available	1 of 2 changes
Grok Build 0.1 xAI · Available	1 of 2 changes
Claude Opus 5 Anthropic · Own key	1 of 1 change
Claude Opus 5.5 Anthropic · Own key	1 of 1 change
GLM-5 Zhipu · Not in Taskade	1 of 1 change
GPT-6.1 Sol OpenAI · Available	1 of 1 change
Grok 4.6 xAI · Available	1 of 1 change
Claude Haiku 4.5 Anthropic · Own key	0 of 2 changes
Claude Sonnet 4.5 Anthropic · Retired	0 of 2 changes
Grok 4.20 xAI · Not in Taskade	0 of 2 changes
Grok 4.3 xAI · Retired	0 of 2 changes
DeepSeek V3.2 DeepSeek · Not in Taskade	0 of 1 change
GLM-4.7 Zhipu · Not in Taskade	0 of 1 change
Kimi K3 Moonshot · Available	0 of 1 change
Mistral Large 4 Mistral · Not in Taskade	0 of 1 change

Build arena

More arenas coming: Automate (AI steps in workflows), Delegate (agents), Research (web research), Answer (chat), and Read (vision).

The full TSK-Bench ranking →Download the data (JSON)

How we grade these apps: read the full method.