xAI · tested in Taskade Genesis
Grok 4.6 in Taskade
Grok 4.6 from xAI runs on the Max and Enterprise plans. We last tested it on Oct 8, 2026 in TSK-1, our app-building test.
- Status
- Available
- Plan
- Max and Enterprise
- Where to pick it
- More models or All Models
- Your own key
- xAI
- Last test
- Context window
- 500Ktokens
- Max output
- 500Ktokens
- Released
- Knowledge cutoff
- Where it runs
- 7services
TSK-1 scorecard for the Grok family
TSK Score
Grok family, across real apps made in Taskade Genesis
- Interfaceready to share
- Strong
- Taskcompletes your task
- Strong
- Memorykeeps your data
- Strong
- Adapthandles follow-up edits
- Strong
Working apps on both August tests, and both follow-up edits landed.
MoreLess
In September it built rich sign-up data across four pages, then added a sign-in screen nobody asked for.
Published scores
Benchmark scores that xAI and test sites published for Grok 4.6. Taskade did not re-run them. Lab-reported marks a score from xAI itself.
| Benchmark | Score | Source |
|---|---|---|
| Terminal-Benchv4.0 · high effort · xAILab-reported | 20.3 | xAILab-reported |
More published scores (7)
| Benchmark | Score | Source |
|---|---|---|
| CursorBenchv4.0 · high effort · xAILab-reported | 40.4 | xAILab-reported |
| DeepSWEv1.1 · high effort · xAILab-reported | 65.2 | xAILab-reported |
| EEBenchhigh effort · xAILab-reported | 53 | xAILab-reported |
| AA-BriefcaseElo · v1.1 · high effort · xAILab-reported | 1,546 | xAILab-reported |
| Harvey Legal Agent Benchmarkhigh effort · xAILab-reported | 15.8 | xAILab-reported |
| HealthBenchhigh effort; professional · xAILab-reported | 48.5 | xAILab-reported |
| GDPvalElo · high effort · xAILab-reported | 1,605 | xAILab-reported |
LMArena scores
| Benchmark | Score | Source |
|---|---|---|
| Text arena±5 · 28,965 votes · Rank 73 of 416 · LMArena | 1,454 | LMArena |
| WebDev arena±7 · 10,363 votes · Rank 26 of 145 · LMArena | 1,617 | LMArena |
Scores from the LMArena leaderboard dataset (CC BY 4.0). People vote between two answers, and the votes set the score. Taskade picked the Overall category and the default setting of each model.
Scores collected by models.dev (MIT). Each source links the page that published the score.
Versions tested
Open a version to read its findings.
Grok 4.6Tested Oct 20266 findings
Working apps on both August tests, and both follow-up edits landed. In September it built rich sign-up data across four pages, then added a sign-in screen nobody asked for.
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.
Took the full 32-question sign-up form into a 58-field table and four pages, with 31 of 32 questions word for word, then added a sign-in screen.
Built the family intake form in 14 minutes so it saved every answer and both photos, and added the new teacher question cleanly. Its teacher page showed three sample families as if they were real.
Model facts
The token limits are the most the model accepts. Taskade can run it with lower limits.
- Last updated
- Input types
- Text, Images, PDF
- Output types
- Text
- Reasoning
- Yes
- Tool calling
- Yes
- File attachments
- Yes
- Structured output
- Yes
- Open weights
- No
- Reasoning effort
- LowMediumHighExtra high
Published specs from the model maker, via models.dev (MIT).
Run Grok 4.6 with your own key
Taskade runs it for you. You can also pick it with your own key in a custom agent.
| Key provider | Plan |
|---|---|
| xAI | Business and up |
Where it runs
Services outside Taskade that serve Grok 4.6, from models.dev. Each link opens in a new tab. In Taskade, your own key works only through the key providers on this page.
How to choose Grok 4.6
- In the builder chat, open the model menu and choose More models. Then pick the model.
- In the agent editor, pick the model under All Models.
- If your model menu does not show the model, Taskade uses TSK-Auto instead.
Where Grok ranks
TSK Score out of 100.
Compare Grok
Other xAI models
FAQ
Which Taskade plans include Grok 4.6?
Grok 4.6 runs in Taskade on the Max and Enterprise plans. If your model menu does not show it, Taskade uses TSK-Auto instead.
Has Taskade tested Grok 4.6?
Yes. We last tested Grok 4.6 on Oct 8, 2026 in the TSK-1 Benchmark. Working apps on both August tests, and both follow-up edits landed. In September it built rich sign-up data across four pages, then added a sign-in screen nobody asked for.
How do I choose Grok 4.6 in Taskade?
In the builder chat, open the model menu and choose More models. Then pick Grok 4.6. In the agent editor, pick it under All Models.
Can I use my own API key for Grok 4.6?
Yes. In a custom agent, you can pick Grok 4.6 with your own key from xAI (Business and up). Your provider bills the model use to your own account.
Who makes Grok 4.6?
xAI makes Grok 4.6. Taskade runs it on the Max and Enterprise plans, beside frontier models from other top AI labs.