Coding Agents · Comparison · No score yet
Cursor vs Claude Code
A fact sheet for builders. ShipRanked has not published test scores for Cursor or Claude Code, and this page does not name a winner.
In one paragraph
ShipRanked has not published a test score for Cursor or Claude Code, so this comparison does not name a winner. Cursor runs as Desktop IDE. Public price: Free, Plus $8/mo, Premium $30/mo, Super $100/mo, Ultra $200/mo. Claude Code runs as Terminal and desktop. Public price: Included with Claude Pro at $20/mo ($17/mo annual). Both are queued for “Add a feature and tests” and “Fix a seeded bug”. That queue is not a ranking. A published score is the median of three runs, from 0 to 100, and the top 3 stays empty until those runs are fresh.
Side by side
Facts checked October 15, 2026. Best-fit is not a verdict. Both tools are still in the test queue.
Price
Cursor. Free, Plus $8/mo, Premium $30/mo, Super $100/mo, Ultra $200/mo
Claude Code. Included with Claude Pro at $20/mo ($17/mo annual)
Where it runs
Cursor. Desktop IDE
Claude Code. Terminal and desktop
Model choice
Cursor. Included usage covers Cursor models: Grok 4.7, Grok 4.6, Grok 4.5, and Composer 2.5. Free and Plus do not include third-party models or your own API keys. Premium and above can use third-party models at API list price.
Claude Code. Claude models. You switch with /model among the Fable, Opus, Sonnet, and Haiku aliases. On the Anthropic API those resolve to Fable 5.1, Opus 5.5, Sonnet 5.5, and Haiku 5.5. Console, Bedrock, Foundry, and Google Cloud still serve Claude models. This is not a bring-any-provider tool.
Open source
Cursor. Closed source
Claude Code. Closed source
Best-fit job
Cursor. Not measured. Queued for Add a feature and tests; Fix a seeded bug.
Claude Code. Not measured. Queued for Add a feature and tests; Fix a seeded bug.
Where to read the queue
Add a feature plus tests to a seeded repo
The agent gets the TaskBoard repo at a pinned commit and a written feature spec. It may edit application code and add tests. A hidden suite the agent does not see decides the pass.
Fix a seeded bug in a repository
A known bug is planted in TaskBoard. The agent has to find and fix it. The rest of the suite has to stay green, and the fix should not be a rewrite.