TSK-1 · xAI · tested in Taskade Genesis
How Grok builds in Taskade Genesis
Updated · Last measured
TSK-1 Score
Aggregated from hands-on Taskade Genesis builds · September 2026
- Interfaceready to share
- Strong
- Taskfollows your request
- Emerging
- Memorykeeps your data
- Strong
- Adapthandles follow-up edits
- Strong
Best for
Follow-up edits that land, at a high price
Grok gets there, slowly. Both of its August apps worked and both follow-up changes landed, which few models manage. Cost was the story: it repeated failed steps dozens of times and spent far more than the leaders on the same requests.
Model results
Grok 4.6Tested Aug 20264 findings
Working apps on both tests, and both follow-up edits landed. It struggled to hand data to the workspace, repeating failed steps dozens of times, so each build took far longer and cost far more than the leaders.
Built a working match tracker with every asked piece, then ended without telling the user it was done.
Took the full 32-question sign-up form and saved every answer, but spread the data across ten projects where the leader used two.
Both follow-up edits landed: a ranked heroes page, and a text score field with next-step suggestions.
Dozens of failed build actions on each app made it one of the slowest and most expensive results of the test.
Grok Build 0.1Tested Aug 20261 finding
Not scored. It described every layer of the build, then repeated the same failed step hundreds of times until the test was stopped. A newer version can earn a fresh test.
Produced no projects, agents, or app: hundreds of failed build actions and no finished work.
App kits you can open today
Live apps from the official Taskade account, not builds by Grok. Each is the same shape every benchmark request asks for: projects, agents, and automations you can open and clone.
- PORTALProduct storefront3 projects · 1 agent · 4 flows
- CRMSales CRM3 projects · 1 agent · 2 flows
- DASHBOARDSales pipeline dashboard3 projects · 1 agent
- PORTALClient portal3 projects · 1 agent · 4 flows
- DASHBOARDGrowth dashboard3 projects · 1 agent · 1 flow
- CRMLead pipeline tracker4 projects · 2 agents · 3 flows
Compare Grok
FAQ
What is Grok best at in Taskade Genesis?
Follow-up changes. Grok 4.6 was one of the few models to land both edits we asked for on its August apps, and both apps worked. The trade-off is cost and time: it repeated failed steps dozens of times and spent far more than the leaders on the same requests.
Why is Grok Build 0.1 listed with no result?
Because it produced no app. It described every layer of the build and then repeated the same failed step hundreds of times until we stopped the test. We publish the tests that go badly alongside the ones that go well.
Can I use Grok in Taskade?
Yes. Grok is available in Taskade alongside 15+ frontier models from OpenAI, Anthropic, and open-weight providers.