Claude Sonnet 5.5
Documented model
Open original sourceSource checked: Oct 3, 2026
AI coding tools
Cursor
A familiar code editor centered on codebase context and agentic editing.
Good fit for
Developers who want AI inside a VS Code-like daily workflow.
Strengths
- Codebase context and agent editing inside a code editor.
Things to consider
- Model selection and automatic routing affect usage charges.
Pricing and plans
Hobby free entry; paid individual and team plans. Model choice affects included usage and additional charges.
Plan structures reflect the documented source date. Check current prices and limits with the provider.
Source checked: Oct 3, 2026
Visit official siteUser reviews
Read user reviews on the original platform. Each source covers the full product, not just its AI features.
Models and independent evidence
A model benchmark describes the tested model and task. It does not measure the whole tool, its interface, or every available plan.
The model names shown are documented examples, not a complete list. Available choices depend on the plan, mode, account and organization settings.
GPT-5.6 Sol
Documented model
Open original sourceSource checked: Oct 3, 2026
Gemini 3.1 Pro
Documented model
Open original sourceSource checked: Oct 3, 2026
Sources
- Official plans · Oct 3, 2026
- Supported models and model billing · Oct 3, 2026
- Agent workflow and checkpoints · Oct 3, 2026
Benchmarks
A model benchmark describes the tested model and task. It does not measure the whole tool, its interface, or every available plan.
BigCode project
BigCodeBench
BigCode project · Function-level code generation. What it measures: Programming task pass rate. Complete and Instruct use different prompts; Full and Hard use different task sets. Match them before comparing results.
- Scope
- Function-level code generation
- What it measures
- Programming task pass rate
Datacurve
DeepSWE
Datacurve · Coding models in the evaluator’s agent. What it measures: Repository task completion. Version 1.1 grades committed code changes in a separate environment. Results depend on the tested agent and reasoning configuration.
- Scope
- Coding models in the evaluator’s agent
- What it measures
- Repository task completion
Documented models with evaluation sources
These model names appear in both the product documentation and an external evaluation. Endpoint revisions, settings and the complete tool workflow have not been matched.
Cursor · GPT-5.6 Sol
Product documentation · External evaluation
DeepSWE tests models with mini-swe-agent, not this product’s agent. Evaluator configuration: gpt-5.6-sol[max] · v1.1
Source checked: Oct 3, 2026