Anthropic · preview runs only
Claude Opus 4.6 and Taskade
Claude Opus 4.6 from Anthropic is not in the Taskade model menu. We ran it in preview tests, which the TSK-1 ranking does not count. Its newest preview run was on Oct 23, 2026. TSK-1, our app-building test, does not rank preview runs.
- Status
- Not in Taskade
- Context window
- 1MtokensHow much it can read at once
- Max output
- 128KtokensLongest answer it can write
- Released
- Knowledge cutoff
- Newest events it learned about
- Where it runs
- 7servicesOther services that serve it
Published scores
Benchmark scores that Anthropic and test sites published for Claude Opus 4.6. Taskade did not re-run them. Lab-reported marks a score from Anthropic itself.
| Benchmark | Score | Source |
|---|---|---|
| SWE-Bench Proresolve rate · publicScale AI | 51.9% | Scale AI |
| Terminal-Benchfirst try · v2.1 · medium effort · in Claude CodeArtificial Analysis | 70.2% | Artificial Analysis |
More published scores (8)
| Benchmark | Score | Source |
|---|---|---|
| SWE-Atlas Codebase QnAin Claude CodeScale AI | 33.3 | Scale AI |
| SWE-Atlas Codebase QnAin Mini-SWE-AgentScale AI | 30 | Scale AI |
| SWE-Atlas Refactoringin Claude CodeScale AI | 35.58 | Scale AI |
| SWE-Atlas Test Writingin Claude CodeScale AI | 36.67 | Scale AI |
| SWE-Atlas Test Writingin Mini-SWE-AgentScale AI | 36.08 | Scale AI |
| Artificial Analysis Coding Agent Indexaverage, first try · medium effort · in Claude CodeArtificial Analysis | 51.3% | Artificial Analysis |
| SWE-Atlas Codebase QnAfirst try · medium effort · in Claude CodeArtificial Analysis | 71.9% | Artificial Analysis |
| SWE-Bench Profirst try · medium effort · in Claude Code · hard-aaArtificial Analysis | 11.8% | Artificial Analysis |
LMArena scores
| Benchmark | Score | Source |
|---|---|---|
| Text arena±3 · 89,324 votes · Rank 9 of 419 · LMArena | 1,496 | LMArena |
| WebDev arena±5 · 20,576 votes · Rank 52 of 152 · LMArena | 1,537 | 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
Preview runs only, not ranked
Model facts
Published specs from the model maker. A token is about three quarters of a word. Taskade can run the model with lower limits than these.
- Last updated
- Reads
- Text, Images, PDFWhat you can give it
- Writes
- TextWhat it gives back
- Reasoning
- YesThinking a problem through first
- Tool calling
- YesUsing tools, such as web search
- File attachments
- YesReading files that you attach
- Structured output
- YesFilling a set format, such as a table
- Open weights
- NoFree for anyone to download and run
- Thinking levels
- LowMediumHighMaxHow long it can think. Higher is slower and more careful.
Published specs from the model maker, via models.dev (MIT).
Where it runs
Services outside Taskade that serve Claude Opus 4.6, from models.dev. Each link opens in a new tab.
What to pick in Taskade
- Leave TSK-Auto on, and Taskade picks a current model for each request.
- To pick a model yourself, choose one from the model menu.
- To compare, open the models page and read the test results of the models you can pick.
Compare Claude
Other Anthropic models
FAQ
Can I pick Claude Opus 4.6 in Taskade?
No. Claude Opus 4.6 is not in the Taskade model menu, and the key providers in Taskade do not list it by name. TSK-Auto picks a current model for each request. The models page lists the models you can pick now.
Has Taskade tested Claude Opus 4.6?
Only in preview runs, last on Oct 23, 2026. The TSK-1 ranking does not count them, so Claude Opus 4.6 has no TSK-1 score. The TSK-1 page shows what each run built.
Who makes Claude Opus 4.6?
Anthropic makes Claude Opus 4.6. Taskade runs frontier models from top AI labs, and the Claude results page shows how Anthropic models build apps.