
Tab Completion
Cursor · Cursor
AI Code Editor — Cursor
Evaluates Cursor's Tab Completion across 6 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's AI Code Editor eval coverage.
About Cursor
Cursor is an AI code editor built on VS Code: predictive Tab completion, inline edits, and an agent mode that plans and executes multi-file changes with terminal access, codebase indexing, project rules, and MCP integration.
Sample tests· showing 3 of 6
| # | Input | Expected behavior | Check |
|---|---|---|---|
| 01 | TypeScript `src/routes/invoices.ts` cursor is inside `async (req, res) => {` after `try {`. Tab offers a single-line `res.json({ ok: true });` ghost text but the handler must validate `req.params.id`, call `billingService.charge`… | Tab suggests a multi-line block covering validation, service call, and catch with `res.status(400|500).json({ error })` matching project patterns; user can Tab-accept full block or partial-accept line-by-line. | Pass / FailCode Completionhigh |
| 02 | File `crates/api/src/handlers/user.rs` already imports `crate::db::DbError` and `User`. Cursor on `match fetch_user(id).await {` with no arm yet. Tab should propose `Ok(user) =>` and `Err(e) =>` arms consistent with Axum `IntoRes… | Completion uses existing imports, does not duplicate `use` lines, and proposes `Err(e)` mapping consistent with neighboring handlers (e.g., `AppError::from(e)`). | Pass / FailCode Completionmedium |
| 03 | Python `services/parser.py` — Tab suggests full `def parse_config(path: str) -> Config:` plus docstring and body. Operator wants signature + type hints only, then will write validation manually. | Partial accept (word/line accept per Tab docs) applies only through the signature line; remaining ghost text stays available or dismisses without inserting full body. | Pass / FailCode Completionlow |
How this eval is graded
Grade against expected.ideal_behavior and expected.rubric. Penalize failure_modes.
Rubric criteria
- Cursor
- Code Assistant
- Tab Completion
Recommended for
Works with
Related evals
Browserbase
Evaluates Browserbase's Captcha Handling across scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Browser infrastructure eval coverage.
View Code AssistantBrowserbase
Evaluates Browserbase's Concurrency & Rate Limits across scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Browser infrastructure eval coverage.
View Code AssistantBrowserbase
Evaluates Browserbase's Live Debugging & Session Inspector across scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Browser infrastructure eval coverage.
ViewFrequently asked questions
What does the Tab Completion eval for Cursor Cursor test?+
Evaluates Cursor's Tab Completion across 6 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's AI Code Editor eval coverage.
How is the Tab Completion eval scored?+
The judge rubric: Grade against expected.ideal_behavior and expected.rubric. Penalize failure_modes.
How many test cases does this eval pack include?+
The Tab Completion pack for Cursor Cursor contains 6 test cases. 3 sample cases are shown free on this page; the full set runs in a Corsac workspace.
How do I run this eval?+
Sign up for Corsac, connect your model or agent endpoint, and run the Tab Completion pack as-is or after customizing thresholds. Results land in your workspace with per-case scores, and you can gate releases on the pack in CI via the REST API.
Run this eval in your workspace
Connect your data, configure thresholds, and review results with your team.