Anthropic · tested in Taskade Genesis
Claude Opus 5 in Taskade
Claude Opus 5 from Anthropic runs on Pro and up, with your own API key. We last tested it on Sep 30, 2026 in TSK-1, our app-building test.
- Status
- Own key
- Plan
- Pro and up, with your own API key (BYOK)
- Where to pick it
- Agent settings
- Your own key
- Anthropic
- Last test
- Context window
- 1Mtokens
- Max output
- 128Ktokens
- Released
- Knowledge cutoff
- Where it runs
- 8services
TSK-1 scorecard for the Claude family
TSK Score
Claude family, across real apps made in Taskade Genesis
- Interfaceready to share
- Strong
- Taskcompletes your task
- Strong
- Memorykeeps your data
- Emerging
- Adapthandles follow-up edits
- Leading
The most complete client sign-up build of September: five pages, every question in the customer's wording, and a scoring automation that ran and saved its verdict.
Published scores
Benchmark scores that Anthropic and test sites published for Claude Opus 5. Taskade did not re-run them. Lab-reported marks a score from Anthropic itself.
| Benchmark | Score | Source |
|---|---|---|
| SWE-Bench Verifiedresolved · AnthropicLab-reported | 96% | AnthropicLab-reported |
| SWE-Bench Proresolve rate · AnthropicLab-reported | 79.2% | AnthropicLab-reported |
| OSWorldsuccess rate · v2.0 · AnthropicLab-reported | 70.6% | AnthropicLab-reported |
| BrowseCompaccuracy · single agent · AnthropicLab-reported | 90.8% | AnthropicLab-reported |
| Humanity's Last Examaccuracy · no tools · AnthropicLab-reported | 56.3% | AnthropicLab-reported |
| ARC-AGI-2accuracy · max effort · AnthropicLab-reported | 90.4% | AnthropicLab-reported |
More published scores (13)
| Benchmark | Score | Source |
|---|---|---|
| SWE-Bench Multilingualresolve rate · AnthropicLab-reported | 89.5% | AnthropicLab-reported |
| SWE-Bench Multimodalresolve rate · AnthropicLab-reported | 59.4% | AnthropicLab-reported |
| DeepSWEresolve rate · v1.1 · AnthropicLab-reported | 68.8% | AnthropicLab-reported |
| FrontierCodemean@5 · v1.1 · medium effort · Main · AnthropicLab-reported | 53.4 | AnthropicLab-reported |
| Frontier-Benchmean reward · v0.1 · max effort · mini-SWE-agent · AnthropicLab-reported | 43.3 | AnthropicLab-reported |
| Humanity's Last Examaccuracy · with tools · AnthropicLab-reported | 64.7% | AnthropicLab-reported |
| DeepSearchQAF1 · max effort · AnthropicLab-reported | 95 | AnthropicLab-reported |
| GDPval-AAElo · v2 · max effort · AnthropicLab-reported | 1,861 | AnthropicLab-reported |
| AA-BriefcaseElo · max effort · AnthropicLab-reported | 1,720 | AnthropicLab-reported |
| AutomationBenchsuccess rate · max effort · AnthropicLab-reported | 26% | AnthropicLab-reported |
| ARC-AGI-1accuracy · max effort · AnthropicLab-reported | 97.5% | AnthropicLab-reported |
| ARC-AGI-3RHAE · high effort · AnthropicLab-reported | 30.2 | AnthropicLab-reported |
| HealthBench Professionalmax effort · AnthropicLab-reported | 59.8 | AnthropicLab-reported |
LMArena scores
| Benchmark | Score | Source |
|---|---|---|
| Text arena±4 · 66,824 votes · Rank 15 of 416 · LMArena | 1,490 | LMArena |
| WebDev arena±5 · 24,516 votes · Rank 14 of 145 · LMArena | 1,658 | 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. We ran these tests with an API key from the lab.
Claude Opus 5Tested Sep 20267 findings
The most complete client sign-up build of September: five pages, every question in the customer's wording, and a scoring automation that ran and saved its verdict.
Set the design high-water mark with a polished, consistent interface.
Created the fullest workspace, with an assistant that understood its contents.
The most complete client sign-up build of the test: a five-page form, every answer saved, and the scoring automation graded the submission on its own.
Best-executed match tracker of the test, without a single failed build action, at by far the highest cost.
Finished the client sign-up form with all 32 questions in the customer's wording, 31 word for word, five pages, and a scoring automation that saved its result.
Decided two open points in the brief and named both decisions in its closing summary.
Built the family intake form so it saved every answer and both photos, and its email automation ran three times. It cost far more than Claude Opus 5.5 on the same request for a lower result.
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 highMax
Published specs from the model maker, via models.dev (MIT).
Run Claude Opus 5 with your own key
Pick it with your own key in a custom agent.
| Key provider | Plan |
|---|---|
| Anthropic | Pro and up |
Where it runs
Services outside Taskade that serve Claude Opus 5, 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 Claude Opus 5
- Open the agent settings.
- Under AI Model, choose the model.
- Under Bring Your Own Key, add or select your provider key.
Where Claude ranks
TSK Score out of 100.
Compare Claude
Other Anthropic models
FAQ
Which Taskade plans include Claude Opus 5?
Claude Opus 5 runs on Pro and up, with your own API key. Your provider bills the model use to your own account.
Has Taskade tested Claude Opus 5?
Yes. We last tested Claude Opus 5 on Sep 30, 2026 in the TSK-1 Benchmark. The most complete client sign-up build of September: five pages, every question in the customer's wording, and a scoring automation that ran and saved its verdict.
How do I choose Claude Opus 5 in Taskade?
Open the agent settings. Under AI Model, choose Claude Opus 5. Under Bring Your Own Key, select your provider key.
Can I use my own API key for Claude Opus 5?
Yes. In a custom agent, you can pick Claude Opus 5 with your own key from Anthropic (Pro and up). Your provider bills the model use to your own account.
Who makes Claude Opus 5?
Anthropic makes Claude Opus 5. Taskade runs it on Pro and up, with your own API key, beside frontier models from other top AI labs.